Suspension control method, device, equipment and medium

Abstract

The embodiment of the invention provides a suspension control method and device suitable for a user outside a vehicle, equipment and a medium, and aims to improve the user experience and the response stability of a suspension. The method comprises the following steps: in response to a received interaction instruction, acquiring a collected image, and determining key point position information of a user in the collected image; wherein the key point position information comprises first position information of a reference point and second position information of an interaction target point; determining a first motion parameter of the suspension based on a relative position relationship between the reference point and the interaction target point; and controlling the suspension to move based on the first motion parameter.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle control, and particularly to a suspension control method, device, equipment, and medium. Background Art

[0002] In the related art, the suspension is mainly controlled according to the driving state of the vehicle during driving, or the road surface feedback situation (sensor-collected data and / or road surface information simulation algorithm); mainly focusing on the suspension control in the scenario where the user is in the vehicle cockpit. With the development of vehicle control technology, the interaction demand between the user and the vehicle increases, and there is an urgent need for a suspension control method applicable to the user outside the vehicle. Summary of the Invention

[0003] Based on this, in view of the above technical problems, it is necessary to provide a suspension control method, device, equipment, and medium to improve the user experience and the response stability of the suspension.

[0004] In a first aspect, an embodiment of the present application provides a suspension control method, including:

[0005] In response to receiving an interaction instruction, acquire a captured image, and determine the key point position information of the user in the captured image; wherein, the key point position information includes the first position information of a reference point and the second position information of an interaction target point;

[0006] Based on the relative position relationship between the reference point and the interaction target point, determine the first motion parameter of the suspension;

[0007] Based on the first motion parameter, control the movement of the suspension.

[0008] In one embodiment, the determining the first motion parameter of the suspension based on the relative position relationship between the reference point and the interaction target point includes:

[0009] Based on the relative position relationship, determine the second motion parameter of the interaction target point; wherein, the interaction target point corresponds to the reference point of the suspension, and the second motion parameter includes a motion direction and / or a motion distance;

[0010] Based on the second motion parameter, determine the first motion parameter.

[0011] In one embodiment, the reference point includes a first reference point corresponding to the middle region of the user's posture;

[0012] The determining the first motion parameter of the suspension based on the relative position relationship between the reference point and the interaction target point includes:

[0013] Determine the first motion parameter based on the relative position relationship between the first reference point and the interaction target point.

[0014] In one embodiment, the determining the key point position information of the user in the acquired image includes:

[0015] Determine the key points and the key point position information corresponding to the key points.

[0016] In one embodiment, the determining the first motion parameter of the suspension based on the relative position relationship between the reference point and the interaction target point includes:

[0017] Determine the relative position relationship between the reference point and the interaction target point based on the first position information and the second position information;

[0018] Determine the first motion parameter of the suspension based on the relative position relationship.

[0019] In one embodiment, the first motion parameter includes the motion distance of the suspension;

[0020] The determining the first motion parameter of the suspension based on the relative position relationship between the reference point and the interaction target point includes:

[0021] Obtain the first coordinate of the reference point of the suspension;

[0022] Determine a first distance based on the coordinates of the first feature point and the coordinates of the first reference point, and determine a second distance based on the coordinates of the first reference point and the coordinates of the interaction target point;

[0023] Determine the motion distance of the suspension according to the first coordinate and the first ratio between the second distance and the first distance.

[0024] In one embodiment, the reference point includes a second reference point corresponding to the shoulder area of the user's posture;

[0025] The first feature point is obtained by processing the first reference point and the second reference point through a first preset rule.

[0026] In one embodiment, the determining the first distance based on the coordinates of the first feature point and the coordinates of the first reference point, and the determining the second distance based on the coordinates of the first reference point and the coordinates of the interaction target point includes:

[0027] Determine the first distance based on the ordinate of the first feature point and the ordinate of the first reference point;

[0028] Determine the second distance based on the ordinate of the first reference point and the ordinate of the interaction target point.

[0029] Since the suspension shows the characteristic of moving upward or downward as a whole during movement, and its coordinate changes in the horizontal or depth direction can be ignored, directly determining the first distance and the second distance through the ordinate can effectively improve the efficiency of determining the first motion parameter and achieve the purpose of saving computing power while ensuring the suspension response stability and user experience.

[0030] In one embodiment, determining the movement distance of the suspension according to the first coordinate and a first ratio between the second distance and the first distance includes:

[0031] Determine the movement distance of the suspension according to the product of the ordinate of the first coordinate, a preset suspension control coefficient, and the first ratio.

[0032] In one embodiment, in the acquired image, determining the first detection frame including the user by matching a first type of detection frame obtained by target detection and a second type of detection frame obtained by trajectory prediction includes:

[0033] In response to the matching parameter between the first type of detection frame and the second type of detection frame in the nth frame of the acquired image being less than a preset first matching parameter threshold, determine the first detection frame of the user in the nth frame of the acquired image based on the first type of detection frame in the (n - 1)th frame of the acquired image; where n is an integer and 2 ≤ n ≤ N.

[0034] In one embodiment, the first motion parameter includes the movement direction type of the suspension;

[0035] The determining of the first motion parameter of the suspension based on the relative position relationship between the reference point and the interaction target point includes:

[0036] In response to a first difference between the ordinate of the second position information and the ordinate of the first reference point being less than a preset first target threshold, determine that the movement direction type is the first direction type; or,

[0037] In response to the first difference being greater than or equal to the first target threshold, determine that the movement direction type is the second direction type;

[0038] Wherein, the first direction corresponding to the first direction type is opposite to the second direction corresponding to the second direction type.

[0039] In one embodiment, the movement distance in the first motion parameter is determined by the following method:

[0040] Determine the second distance and determine a fourth distance corresponding to the type of movement direction;

[0041] Based on the ratio of the second distance to the fourth distance as a second ratio; wherein, the second ratio corresponds to the type of movement direction;

[0042] Based on a preset suspension control coefficient, the second ratio, and an extreme height corresponding to the type of movement direction, determine the movement distance.

[0043] In one embodiment, the determining the fourth distance corresponding to the type of movement direction includes:

[0044] In response to the type of movement direction being a first direction type, determine the distance between the first feature point and the first reference point as the fourth distance;

[0045] Or,

[0046] In response to the type of movement direction being a second direction type, determine the distance between the first reference point and a second feature point as the fourth distance; wherein, the second feature point corresponds to the bottom region of the user posture,

[0047] The second feature point is obtained by processing the second reference point and the first reference point through a second preset rule.

[0048] In one embodiment, the movement distance is determined according to the following formula:

[0049] wherein, D g is the movement distance corresponding to the type of movement direction, h max is the extreme height corresponding to the type of movement direction, k is a preset suspension control coefficient, D 4 is the fourth distance corresponding to the type of movement direction, D 2 is the second distance.

[0050] In one embodiment, the determining the key point position information of the user in the acquired image includes:

[0051] In N frames of the acquired image, determine a first detection frame containing the user by matching a first type of detection frame obtained by target detection and a second type of detection frame obtained by trajectory prediction; N is an integer greater than or equal to 2;

[0052] In the first detection frame of the acquired image, determine the key points and the key point position information of the user.

[0053] In one embodiment, in the acquired image, determining a first detection box containing the user by matching a first type of detection box obtained by target detection with a second type of detection box obtained by trajectory prediction includes:

[0054] Performing target detection on the acquired image to obtain the first type of detection box; wherein, the first type of detection box includes a second detection box in the (n - 1)-th frame of the acquired image and a third detection box in the n-th frame of the acquired image, n is an integer, and 2 ≤ n ≤ N;

[0055] Predicting the trajectory of the user in the second detection box in the (n - 1)-th frame of the acquired image to obtain a fourth detection box in the n-th frame of the acquired image;

[0056] For the n-th frame of the acquired image, in response to the matching parameter between the third detection box and the fourth detection box being less than a preset second matching parameter threshold, correcting the third detection box in the n-th frame of the acquired image based on the second detection box to obtain the first detection box.

[0057] In this embodiment, by matching the first type of detection box obtained by target detection with the second type of detection box obtained by trajectory prediction, the accuracy of the recognized user is achieved. On this basis, when the matching parameter is less than the second matching parameter threshold, correcting the third detection box can effectively avoid the situation where the matching parameter is less than the second matching parameter threshold due to factors such as jitter, misdetection, or missed detection of target detection, resulting in the misjudgment that the n-th frame of the acquired image does not contain the first detection box and interrupting the suspension control, thereby further improving the accuracy of the determined first detection box and user recognition, and further improving the response stability of the suspension.

[0058] In one embodiment, correcting the third detection box in the n-th frame of the acquired image based on the second detection box to obtain the first detection box includes:

[0059] Based on the time stamp carried by the acquired image, determining a first number of the acquired images before the n-th frame of the acquired image as a target image sequence;

[0060] In response to the acquired images in the target image sequence including the first detection box, correcting the third detection box in the n-th frame of the acquired image to obtain the first detection box.

[0061] In this embodiment, by verifying the target image sequence before the nth frame of the captured image, it is identified whether the failure of the third detection box and the fourth detection box to match in the nth frame of the captured image is a misdetection situation caused by factors such as jitter in target detection and / or trajectory prediction. Then, by correcting the third detection box in the nth frame of the captured image, the accuracy of the first detection box can be further improved, that is, the accuracy of the identified user can be improved, thereby avoiding prematurely ending the suspension control incorrectly or ending the interaction before the user has left the vehicle, and still controlling the suspension movement according to the first motion parameters corresponding to the first detection box in the previous few frames of the captured image, further improving the response stability of the suspension.

[0062] In one embodiment, after predicting the trajectory of the user in the second detection box in the (n - 1)th frame of the captured image to obtain the fourth detection box in the nth frame of the captured image, it further includes:

[0063] In response to the matching parameter between the third detection box and the fourth detection box being greater than or equal to the second matching parameter threshold, it is determined that the third detection box in the nth frame of the captured image is the first detection box.

[0064] In one embodiment, determining the key points and the key point position information of the user in the first detection box of the captured image includes:

[0065] Based on the information of the first detection box, in the captured image, determining the feature information of the pose points; wherein, the feature information includes the category information of the pose points;

[0066] According to the category information of the pose points, determining the reference point and the interaction target point; then obtaining the key points and the key point position information.

[0067] In one embodiment, the key point position information is the ordinate of the key point; then the first position information is the ordinate of the reference point, and the second position information is the ordinate of the interaction target point.

[0068] In one embodiment, determining the first motion parameter of the suspension based on the relative position relationship between the reference point and the interaction target point includes:

[0069] In the captured image, determining the reference point and determining the interaction target point corresponding to the user's hand; wherein, the reference point includes the first reference point and the second reference point;

[0070] Determine the first motion parameter based on the relative position relationship between the interaction target point, the first reference point, and the second reference point, and the posture information of the hand.

[0071] In a second aspect, an embodiment of the present application provides a suspension control device, including:

[0072] An instruction module, configured to obtain a captured image and determine the key point position information of the user in the captured image in response to receiving an interaction instruction; where N is an integer greater than or equal to 2, and the key point position information includes the first position information of the reference point and the second position information of the interaction target point;

[0073] A parameter module, configured to determine the first motion parameter of the suspension based on the relative position relationship between the reference point and the interaction target point;

[0074] A motion module, configured to control the movement of the suspension based on the first motion parameter.

[0075] In one embodiment, the instruction module is specifically configured to determine the key points and the key point position information corresponding to the key points.

[0076] In one embodiment, the parameter module is specifically configured to determine the second motion parameter of the interaction target point based on the relative position relationship; where the interaction target point corresponds to the reference point of the suspension; and determine the second motion parameter as the first motion parameter.

[0077] In one embodiment, the parameter module is specifically configured to determine the relative position relationship between the reference point and the interaction target point based on the first position information and the second position information; and determine the first motion parameter of the suspension based on the relative position relationship.

[0078] In one embodiment, the reference point includes a first reference point corresponding to the middle region of the user's posture; the parameter module is specifically configured to determine the first motion parameter based on the relative position relationship between the first reference point and the interaction target point.

[0079] In one embodiment, the first motion parameter includes the movement distance of the suspension; the parameter module is specifically configured to obtain the first coordinate of the reference point of the suspension; determine a first distance based on the coordinates of the first feature point and the coordinates of the first reference point, and determine a second distance based on the coordinates of the first reference point and the coordinates of the interaction target point; and determine the movement distance of the suspension according to the first coordinate and the first ratio between the second distance and the first distance.

[0080] In one embodiment, the parameter module is specifically configured to determine the first distance based on the ordinate of the first feature point and the ordinate of the first reference point; and determine the second distance based on the ordinate of the first reference point and the ordinate of the interaction target point.

[0081] In one embodiment, the first motion parameter includes the motion distance of the suspension; then the parameter module is specifically configured to obtain the first coordinate of the reference point of the suspension; determine the first distance based on the coordinates of the first feature point and the coordinates of the first reference point, and determine the second distance based on the coordinates of the first reference point and the coordinates of the interaction target point; and determine the motion distance of the suspension according to the first coordinate and the first ratio between the second distance and the first distance.

[0082] In one embodiment, the first motion parameter includes the type of the motion direction of the suspension; then the parameter module is further configured to determine that the type of the motion direction is the first direction type in response to that the first difference between the ordinate of the second position information and the ordinate of the first reference point is less than a preset first target threshold; or determine that the type of the motion direction is the second direction type in response to that the first difference is greater than or equal to the first target threshold; wherein, the first direction corresponding to the first direction type is opposite to the second direction corresponding to the second direction type.

[0083] In one embodiment, the parameter module is further configured to determine a fourth distance corresponding to the type of the motion direction, and an extreme height of the suspension corresponding to the type of the motion direction; determine the second distance; wherein, the second distance is the distance between the coordinates of the first reference point and the interaction target point; determine a second ratio of the second distance to the fourth distance; wherein, the second ratio corresponds to the type of the motion direction; and determine the motion distance based on the second ratio, a preset suspension control coefficient, and the extreme height corresponding to the type of the motion direction.

[0084] In one embodiment, the parameter module is further configured to determine that the distance between the first feature point and the first reference point is the fourth distance in response to that the type of the motion direction is the first direction type; or determine that the distance between the first reference point and a second feature point is the fourth distance in response to that the type of the motion direction is the second direction type; wherein, the second feature point corresponds to the bottom area of the user posture, and the second feature point is obtained by processing the second reference point and the first reference point through a second preset rule.

[0085] In one embodiment, the parameter module is further configured to: wherein, D gh is the movement distance corresponding to the movement direction type max k is the extreme height corresponding to the movement direction type, and k is a preset suspension control coefficient, D 4 D is the fourth distance corresponding to the movement direction type, D 2 is the second distance

[0086] In one embodiment, the instruction module is specifically configured to, in the acquired image, determine a first detection frame containing the user by matching a first type of detection frame obtained by target detection with a second type of detection frame obtained by trajectory prediction; in the first detection frame of the acquired image, determine the key points of the user and the key point position information

[0087] In one embodiment, the instruction module is specifically configured to, in response to a matching parameter between the first type of detection frame and the second type of detection frame in the nth frame of the acquired image being less than a preset first matching parameter threshold, determine the first detection frame of the user in the nth frame of the acquired image based on the first type of detection frame in the (n - 1)th frame of the acquired image; where n is an integer and 2 ≤ n ≤ N

[0088] In one embodiment, the instruction module is specifically configured to perform target detection on the acquired image to obtain the first type of detection frame; where the first type of detection frame includes a second detection frame in the (n - 1)th frame of the acquired image and a third detection frame in the nth frame of the acquired image, n is an integer and 2 ≤ n ≤ N; predict the trajectory of the user in the second detection frame in the (n - 1)th frame of the acquired image to obtain a fourth detection frame in the nth frame of the acquired image; for the nth frame of the acquired image, in response to a matching parameter between the third detection frame and the fourth detection frame being less than a preset second matching parameter threshold, correct the third detection frame in the nth frame of the acquired image based on the second detection frame to obtain the first detection frame

[0089] In one embodiment, the instruction module is specifically configured to, based on the time stamp carried by the acquired image, determine a first number of the acquired images before the nth frame of the acquired image as a target image sequence; in response to the acquired images in the target image sequence including the first detection frame, correct the third detection frame in the nth frame of the acquired image to obtain the first detection frame

[0090] In one embodiment, the instruction module is further configured to, in response to the matching parameter between the third detection frame and the fourth detection frame being greater than or equal to the second matching parameter threshold, determine the third detection frame of the nth frame of the acquired image as the first detection frame

[0091] In one embodiment, the instruction module is further configured to determine the feature information of the pose points in the acquired image based on the information of the first detection frame; wherein, the feature information includes the category information of the pose points; determine the reference point and the interaction target point according to the category information of the pose points; then obtain the key points and the key point position information.

[0092] In one embodiment, the parameter module is further configured to determine the reference point in the acquired image, and determine the interaction target point corresponding to the user's hand; determine the first motion parameter based on the relative position relationship between the interaction target point and the reference point, and the pose information of the hand.

[0093] In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the steps of the method according to the first aspect and any one of the embodiments are implemented.

[0094] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method according to the first aspect and any one of the embodiments are implemented.

[0095] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, the steps of the method according to the first aspect and any one of the embodiments are implemented.

[0096] The above suspension control method, device, electronic device and storage medium determine the key point position information of the user in the acquired image, and determine the first motion parameter matching the user's height for the suspension, so as to control the motion of the suspension according to the first motion parameter, enabling the suspension to more accurately understand the user's interaction intention and adaptively move with the change of the user's pose. While improving the interaction effect and user experience, this method also effectively improves the response stability of the suspension, avoiding problems such as insufficient response stability of the suspension caused by the user being too tall or too short (for example, children), or not matching the user's interaction intention.

[0097] Other features and advantages of the present application will be described in the subsequent specification, and, in part, will be obvious from the specification, or will be understood by implementing the present application. The objectives and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written specification, claims, and drawings. It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0098] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only the embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained according to the provided drawings.

[0099] Figure 1 It is a schematic flowchart of a suspension control method in an embodiment;

[0100] Figure 2A It is a schematic diagram of a user posture including a first feature point in an embodiment;

[0101] Figure 2B It is a schematic diagram of the position of a first reference point in an embodiment;

[0102] Figure 3 It is a schematic diagram of a user posture including a second feature point in an embodiment;

[0103] Figure 4 It is a schematic diagram of an interaction target point of a user in an embodiment;

[0104] Figure 5 It is a schematic flowchart of determining a first detection frame where a user is located in multiple frames of captured images in an embodiment;

[0105] Figure 6 It is a schematic diagram of a suspension control method in an embodiment;

[0106] Figure 7 It is a structural block diagram of a suspension control device in an embodiment;

[0107] Figure 8 It is an internal structure diagram of an electronic device in an embodiment. Detailed implementation manners

[0108] In order to make the objectives, technical solutions and advantages of the present application more clear and understandable, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0109] It should be noted that the illustrations provided in this embodiment only illustrate the basic concept of the present application schematically. Therefore, only the components related to the present application are shown in the drawings, rather than being drawn according to the number, shape, and size of the components in actual implementation. The types, quantities, and proportions of the components in actual implementation can be arbitrarily changed, and the component layout type may also be more complex. The structures, proportions, sizes, etc. shown in the drawings of this specification are only used to cooperate with the content disclosed in the specification for those skilled in this technology to understand and read, and are not used to limit the limiting conditions under which the present application can be implemented. Therefore, they do not have a substantial technical meaning. Any modification of the structure, change of the proportional relationship, or adjustment of the size, without affecting the effects that the present application can produce and the purposes that can be achieved, should still fall within the scope that can be covered by the technical content disclosed in the present application. At the same time, the terms such as "upper", "lower", "left", "right", "middle", and "one" cited in this specification are only for the convenience of clear narration, rather than to limit the scope in which the present application can be implemented. The change or adjustment of their relative relationships, without substantial change in the technical content, should also be regarded as the scope in which the present application can be implemented.

[0110] Reference to "embodiments" in this document means that the specific features, structures, or characteristics described in connection with the embodiments can be included in at least one embodiment of the present application. The phrase appears in various places in the text and does not necessarily refer to the same embodiment each time, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0111] As shown herein, unless the context clearly indicates otherwise, words such as "a", "an", "one", and / or "the" are not specifically singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0112] The definitions included herein, as used herein, the terms "having", "may have", "including", or "may include" indicate the existence of the corresponding functions, operations, elements, etc. of the present application, and do not limit the existence of one or more other functions, operations, elements, etc. In addition, it should be understood that, as used herein, the terms "including" or "having" indicate the existence of the features, numbers, steps, operations, elements, components, or combinations thereof described in the specification, and do not exclude the existence or addition of one or more other features, numbers, steps, operations, elements, components, or combinations thereof.

[0113] In the embodiments of the present application, prefix words such as "first" and "second" are only used to distinguish different described objects, and have no restrictive effect on the position, order, priority, quantity, content, etc. of the described objects. In the embodiments of the present application, the use of prefix words such as ordinal numbers for distinguishing described objects does not constitute a limitation on the described objects. For the statement of the described objects, refer to the description in the claims or the context of the embodiments. It should not constitute an unnecessary limitation because of the use of such prefix words. In addition, in the description of this embodiment, unless otherwise specified, the meaning of "a plurality" is two or more.

[0114] To facilitate understanding of the technical solutions provided by the embodiments of the present application, the following first introduces the design concept of the embodiments of the present application:

[0115] When a user interacts with a vehicle, the stability of the suspension's response (e.g., an active suspension) is crucial. Especially when the user is outside the vehicle, when the user has a need to interact with the vehicle, the information collected by the information collection device carried on the vehicle, and how to process the collected information, have obvious effects on the error contained in the suspension control parameters and the suspension response stability. Taking the aforementioned information collection device as an image collection device as an example, in the process of processing the collected image captured by the image collection device to identify the user's interaction intention and achieve suspension control, the user's height, as well as the distance and angle between the user and the image collection device carried on the vehicle, etc. become the main factors affecting the suspension control parameters. If the suspension directly responds to users with different heights, it is easy for the movement amplitude of the suspension's reference line to be too large, resulting in poor interaction effects, insufficient control accuracy of the suspension by the user, and further problems of poor suspension response stability. The aforementioned reference line of the suspension refers to the horizontal line where the reference point of the suspension is located.

[0116] Therefore, the embodiments of the present application provide a suspension control method, which determines the key point position information of the user and uses the relative position relationship between the interaction target point and the reference point in the key points to determine the first motion parameter of the suspension, thereby avoiding the problem of poor suspension response stability caused by large differences in the generation of the first motion parameter of the suspension when the user is taller or shorter.

[0117] In one embodiment, as Figure 1 shown, a suspension control method is provided, and the method includes the following steps:

[0118] Step 101, in response to receiving an interaction instruction, acquire a captured image and determine the key point position information of the user in the captured image.

[0119] Among them, the key point position information includes the first position information of the reference point and the second position information of the interaction target point.

[0120] Specifically, the representation form of the above key point position information includes, but is not limited to, at least one of two-dimensional coordinates, three-dimensional coordinates, polar coordinates, and longitude and latitude coordinates.

[0121] In one embodiment, the captured image can be obtained by using an image capture device to capture a user image after receiving an interaction instruction. Specifically, since the interaction instruction may contain user information, the user information can be read from the interaction instruction first, and then according to the position information in the user information, the relative position relationship between the user and the vehicle can be determined to determine the image capture device mounted on the vehicle body, and the target area can be captured by using the image capture device.

[0122] Among them, the user information contained in the interaction instruction includes at least the position information of the user, so as to determine the relative position relationship between the user and the vehicle accordingly, and select the image capture device for capturing images among the multiple image capture devices mounted on multiple parts of the vehicle body. The target area in the interaction instruction corresponds to the position information; then the target area can be used to determine the shooting parameters of the image capture device so that the resolution of the captured image is greater than the preset resolution threshold.

[0123] In one embodiment, the response accuracy and stability of the suspension can be improved by improving the accuracy of the user's key point position information. Specifically, the accuracy of the key point position information can be improved by obtaining N captured images to determine the key point position information of the user therein.

[0124] Optionally, after receiving the interaction instruction, the image capture device mounted on the vehicle body can be powered on immediately, and the images in the directions corresponding to the lenses of the image capture device can be captured respectively to obtain the images around the vehicle. Then, the captured image is selected from the image frames according to the position information and the pre-specified target pose.

[0125] The pre-specified target pose can be used to verify the pose of the target in the image frame to quickly identify the first image frame containing the user among multiple image frames. Then, the image frames after the first image frame can all be used as the captured image.

[0126] Optionally, after identifying the aforementioned first image frame, facial enhancement processing can be performed on the target in the first image frame that matches the pre-specified target pose to obtain a facial image with a resolution higher than the resolution threshold. By verifying the facial image, the accuracy of user identification can be improved.

[0127] Then, the image frames after the first image frame are used as the captured image.

[0128] In one embodiment, the aforementioned N captured images can carry time stamps. The time stamp can be, for example, the capture time of the captured image.

[0129] The N captured images can be sorted according to time stamps.

[0130] At least two consecutive images are included in the above-mentioned N captured images.

[0131] In one embodiment, the N captured images can be consecutive image frames, that is, the capture time intervals between image frames are equal, and the capture time interval is less than a preset first time threshold. For example, the capture time intervals are all 1 second or 1 millisecond.

[0132] In one embodiment, the N captured images can include consecutive image frames and non-consecutive image frames. For example, among the N captured images, the capture time intervals between a certain a captured images are equal and less than a preset first time threshold, and the capture time intervals between b captured images are different from each other and less than a preset second time threshold. Where N = a + b.

[0133] Further, the key points corresponding to the foregoing key point position information may include: an interaction target point and a reference point corresponding to the user's hand. The reference point includes a first reference point corresponding to the middle region of the user's posture.

[0134] Optionally, the reference point may further include a second reference point corresponding to the shoulder region of the user's posture.

[0135] In one embodiment, the key points may further include: a first feature point corresponding to the top region of the user's posture, and a second feature point corresponding to the bottom region of the user's posture.

[0136] In one embodiment, the key points may include the foregoing interaction target point, reference point, a first feature point corresponding to the top region of the user's posture, and a second feature point corresponding to the bottom region of the user's posture.

[0137] Preferably, the foregoing user's posture is a standing posture.

[0138] The middle region of the above-mentioned user's posture may be the user's waist region when the user's posture is a standing posture.

[0139] The top region of the user's posture is preferably the region where the user's hand is located when the hand is raised to the highest position in the standing posture.

[0140] The bottom region is preferably the region where the user's hand is located when the user's arm hangs naturally in the standing posture.

[0141] In one embodiment, the first feature point is obtained by processing the second reference point and the first reference point according to a first preset rule.

[0142] In one embodiment, similarly to the first feature point, the second feature point can be obtained by processing the foregoing second reference point and the first reference point according to a second preset rule.

[0143] The above reference points can be used to determine the change range of the position of the interaction target point, so as to determine the reference line of the suspension and the first motion parameter of the suspension along the longitudinal axis. Here, the reference line is the horizontal line where the reference point is located. For example, the first motion parameter can be determined based on the relative position relationship between the first reference point and the interaction target point.

[0144] Since the height change of the reference line during the movement of the suspension is actually a change at the millimeter level. For example, the height change is 10 mm, 20 mm, 30 mm, etc. In order to further improve the response stability of the suspension and the user experience, and to avoid the position change of the reference point of the suspension being too subtle to adapt to the large posture change of the user and reduce the user experience. Preferably, in the embodiments of the present application, the reference point is determined by the height of the area at a preset position in the user's standing posture.

[0145] The following first describes the positional relationship between the reference point and the foregoing first feature point and / or second feature point when the user is in a standing posture:

[0146] In one embodiment, the foregoing first feature point corresponds to the top area of the user's posture. Preferably, the top area of the user's posture can indicate the highest area that the user's hand can reach in the standing posture. Then the top area is the area corresponding to the hand when the user is in the standing posture and the arm state is the raised hand state.

[0147] Figure 2A This is a schematic diagram of a user posture provided by the embodiments of the present application. Please refer to Figure 2A , the first feature point is marked as "★"; then the first feature point can be the center point of the hand when the user's hand is raised to the highest position.

[0148] The first reference point is marked as "●1". The first reference point corresponds to the middle area of the user's posture. The middle area at least partially overlaps with the waist. Then the middle area of the user's posture can be the area corresponding to the user's waist position when the user is in the standing posture. Please refer to Figure 2A , Figure 2B , the first reference point is marked as "●1". The first reference point can be the intersection point of the reference line corresponding to the user's arm when the arm naturally drops and the horizontal reference line corresponding to the user's waist. Then the middle area is the overlapping area between the area extended along the direction of the user's hanging arm and the area extended horizontally (i.e., horizontally) along the user's waist. The second reference point is marked as "●2", and the second reference point corresponds to the shoulder area of the user's posture.

[0149] In one embodiment, the foregoing second feature point corresponds to the bottom area of the user's posture when the user is standing. Please refer to Figure 3, the second feature point is marked as "★", and this second feature point can be the center point of the hand when the user stands with the arm hanging naturally. Then this bottom area is the hand area when the user stands with the arm hanging naturally. The above-mentioned center point of the hand can be the geometric center of the palm when the user spreads the fingers; the center point of the hand can also be the geometric center of the fist when the hand makes a fist, etc.

[0150] In one embodiment, it can be determined by combining relevant detection algorithms with preset rules. The description is as follows:

[0151] First, the first pre-trained detection algorithm can be used to process the acquired image: Based on the information of the first detection box, the feature information of the pose points is determined in the acquired image.

[0152] Among them, the feature information includes the coordinates of the pose points and the category information of the pose points. This first detection algorithm can be, for example, YOLO-Pose. This category information indicates the body parts of the user corresponding to the pose. For example, the aforementioned category information can be at least one of the waist, hand, head, elbow, and shoulder.

[0153] Then, according to the aforementioned category information of the pose points, the reference point and the interaction target point are determined; and the first reference point and the second reference point in the reference points can be processed by using the corresponding preset rules to obtain the first feature point and the second feature point.

[0154] In this way, the key points can be obtained. And the feature information of the aforementioned pose points can also include the coordinates of the pose points, so the key point position information can be determined according to the coordinates of the reference points and the coordinates of the interaction target points in the category information.

[0155] Exemplarily, to obtain the key point position information, the first reference point corresponding to the waist and the second reference point corresponding to the shoulder can be determined first according to the category information. Then, the height difference H between the first reference point and the second reference point is processed by the first preset rule in the preset rules to obtain the first feature point.

[0156] And the height difference H between the second reference point and the first reference point is processed by the second preset rule in the preset rules to obtain the second feature point.

[0157] To improve the efficiency and accuracy of determining the key point position information and save the computing power of the terminal, in one embodiment, the ordinate of the above key point can be directly determined as the key point position information. This ordinate can be obtained through the coordinates in the image coordinate system and / or the physical coordinate system.

[0158] Exemplarily, the foregoing category information includes the shoulder and the waist. The reference points at least include a second reference point corresponding to the shoulder and a first reference point corresponding to the waist. Then, according to the foregoing category information, the second reference point corresponding to the shoulder and the ordinate L of the second reference point corresponding to the shoulder can be determined 1 ; then the ordinate of the first feature point can be determined by using the corresponding preset rules. Moreover, according to the foregoing category information, the ordinate L of the first reference point corresponding to the waist is determined 2 , and the ordinate of the second feature point is determined by using the corresponding preset rules. The foregoing determines the ordinate L of the second reference point corresponding to the shoulder according to the category information of the reference point 1 , and the ordinate L of the first reference point corresponding to the waist 2 .

[0159] Let the absolute value of the difference between L 1 and L 2 be denoted as H. This H represents the distance between the shoulder and the waist.

[0160] Then the first preset rule for determining the ordinate y 1 of the first feature point is: y 1 = α 1 ×H + L 2 ; where α 1 is a preset first coefficient. This first coefficient α 1 can be, for example, 1.6; that is, y 1 = 1.6H + L 2 .

[0161] The ordinate y 2 of the first reference point satisfies: y 2 = L 2 ;

[0162] The second preset rule for determining the ordinate y 3 of the second feature point is: y 3 = L 2 - α 2 ×H. Where α 2 is a preset second coefficient. This second coefficient α 2 can be, for example, 0.3; that is, y 3 = L 2 - 0.3H.

[0163] In this way, through the detected second reference point corresponding to the shoulder and the first reference point corresponding to the waist, according to the first preset rule y 1 = 1.6H + L 2 , the ordinate of the first feature point is obtained.

[0164] Moreover, according to the second preset rule y3 = L 2 - 0.3H to obtain the ordinate of the second feature point.

[0165] Furthermore, in order to improve the response stability of the suspension, in one embodiment, the response stability of the suspension can be improved by enhancing the accuracy of the recognized user posture. Due to the change of the user posture, especially when the user interacts with the vehicle through posture changes, the position change of the user's hand can accurately reflect the user's interaction intention; and, since the hand is an easily recognizable part of the user's body compared to some joints, especially for the position of the hand, the requirements for the image acquisition conditions are relatively low. Therefore, it also has the advantages of low light requirements for the shooting environment and low requirements for the shooting parameters of the image acquisition device, and has a wide range of applications. Therefore, in a possible implementation manner, please refer to Figure 4 , the center point of the user's hand can be used as the interaction target point. Then, after determining the user, the user's hand can be recognized to determine the interaction target point and / or the second position information of the interaction target point.

[0166] Thus, the above reference point is a pre-specified coordinate point, while the interaction target point changes with the user's position and / or posture, etc.

[0167] Exemplarily, the source of the received interaction instruction can be a voice instruction issued by the user.

[0168] Exemplarily, the interaction instruction can be a preset gesture instruction formed by the user through a pre-specified gesture posture.

[0169] Exemplarily, the interaction instruction can also be sent by the user controlling the virtual button on the car machine screen.

[0170] Exemplarily, the interaction instruction can be that the portable terminal held by the user sends a corresponding interaction start identifier.

[0171] The transmission form of the interaction instruction can include but is not limited to sending through Bluetooth signals and / or wireless signals, etc.

[0172] And, the interaction instruction can instruct to start the gesture control suspension movement function, so that the vehicle starts to acquire the collected image to determine the gesture information of the user in the collected image after receiving the interaction instruction. The gesture information can include the relative position relationship between the reference point and the interaction target point described in step 102.

[0173] Step 102, based on the relative position relationship between the reference point and the interaction target point, determine the first motion parameter of the suspension.

[0174] Specifically, the relative position relationship between the reference point and the interaction target point can be determined first based on the first position information of the reference point and the second position information of the interaction target point.

[0175] Then, based on this relative position relationship, determine the first motion parameter of the suspension.

[0176] It can be understood that the response stability of the suspension refers to the ability of the suspension to quickly and accurately respond when the user's interaction intention changes and maintain the stability of the vehicle's attitude and state. Determining the first motion parameter of the suspension according to the relative position relationship between the reference point and the interaction target point can effectively improve the accuracy of the recognized user posture change, thereby improving the response stability of the suspension, and avoiding directly selecting the pre-specified position part of the user as the interaction target point to compare the relative position relationship between this interaction target point and the pre-specified reference point (with fixed coordinates). When different users have different heights, for a user with a higher height, the interaction intention is to move downward, and the coordinates where the interaction target point stops after moving downward are still relatively high, resulting in a problem of reduced response stability of the suspension caused by the suspension moving upward erroneously; or, when a user with a smaller height has an interaction intention to move upward, the coordinates where the interaction target point stops after moving upward are still relatively low, resulting in a significant reduction in the response stability of the suspension caused by the suspension moving downward erroneously.

[0177] The above-mentioned first motion parameter includes, but is not limited to, the type of motion direction and / or the motion distance of the suspension in the vertical direction. The unit of this motion distance can be, for example, millimeters.

[0178] In one embodiment, the above-mentioned first motion parameter includes the motion distance of the suspension. This motion distance can indicate: when taking the position where the reset point is located as the reference coordinate for the suspension movement, the motion distance of the reference point. The reference line where the reference point is located moves synchronously with the reference point. Then the motion distance can also be the distance that the reference point moves away from the reset point along the longitudinal axis.

[0179] Regarding the above-mentioned reference point, the following is an explanation: In the embodiments of the present application, the reference point is located on the suspension. The reference point, the horizontal line where the reference point is located (i.e., the reference line where the reference point is located), and the suspension move together.

[0180] Regarding the above-mentioned reset point, the following is an explanation: In the embodiments of the present application, the reset point is a stationary point. Before the user interacts with the vehicle, the reset point of the suspension can coincide with the reference point. When the user starts to interact with the vehicle, or after the user starts to interact with the vehicle, the suspension moves, and this reset point does not move with the movement of the suspension.

[0181] In one embodiment, the above-mentioned first motion parameter includes the type of motion direction of the suspension. This type of motion direction can indicate the direction in which the reference point of the suspension moves away from the reset point with the reset point as the reference.

[0182] That is, with the reset line as the reference, in the direction perpendicular to the ground, the direction in which the suspension moves away from the reset line. This reset line indicates the horizontal line where the reset point is located.

[0183] Step 103, control the movement of the suspension based on the first motion parameter.

[0184] Specifically, a control signal corresponding to the first motion parameter can be generated based on the first motion parameter, and the control signal is sent to the MCU (Microcontroller Unit) in the suspension domain, so that the MCU controls the movement of the suspension to achieve human-vehicle interaction.

[0185] Further, the foregoing reference line is the horizontal reference line where the reference point is located; then in an embodiment, according to the first motion parameter, control the reference line of the suspension to move along the longitudinal axis following the reference point.

[0186] The longitudinal axis can be the y-axis in a Cartesian coordinate system, an image coordinate system, or a physical coordinate system. The coordinate system here is consistent with the coordinate system for determining the key point position information described in step 101.

[0187] It should be noted that the suspension control method provided by the embodiments of the present application is particularly applicable to the control of active suspensions.

[0188] Since the suspension generally moves upward or downward as a whole when moving, the first motion parameter of the foregoing suspension can be realized by controlling the reference point of the suspension to move based on the first motion parameter. Thus, the movement of the reference point drives the overall movement of the suspension, thereby controlling the movement of the suspension.

[0189] In this way, according to the relative position change between the key points of the user, control the movement of the suspension, realize adaptive control according to users of different heights, so as to accurately understand the user interaction intention, and thus interact with the user by controlling the movement of the suspension, avoiding the problem of unstable suspension response caused by too high or too low reference point coordinates when the reset horizontal line of the suspension moves with the user's posture change due to height differences among different users.

[0190] Further, please continue to refer to Figure 2A 、 Figure 2B . Since the suspension moves with its reference point when the suspension moves, the user can control the reference point of the suspension through the interaction target point to achieve the control of the suspension. The interaction target point corresponds to the reference point of the suspension. Specifically, the second motion parameter of the interaction target point can be determined based on the foregoing relative position relationship. The reference point and the interaction target point are in one-to-one correspondence. Among them, the second motion parameter includes the movement distance and / or the movement direction type. Then, the first motion parameter can be determined based on the second motion parameter.

[0191] For example, if the second motion parameter is the motion distance, the motion distance of the first motion parameter can be determined according to the motion distance in the second motion parameter.

[0192] For example, if the second motion parameter is the motion direction type, the motion direction type in the first motion parameter can be determined according to the motion direction type in the second motion parameter.

[0193] Another example is that if the second motion parameter includes the motion distance and the motion direction type, the motion distance in the first motion parameter can be determined according to the motion distance in the second motion parameter, and the motion direction type in the first motion parameter can be determined according to the motion direction type in the second motion parameter.

[0194] In this way, through the relative position relationship between the aforementioned reference point and the interaction target point, the motion change of the interaction target point can be mapped to the reference point as the second motion parameter, so as to determine the first motion parameter of the suspension (that is, the first motion parameter of the reference point of the suspension), and the suspension can be realized to move following the position change of the user's interaction target point.

[0195] Furthermore, an embodiment is provided below to illustrate the determination of the motion distance in the first motion parameter:

[0196] First, obtain the first coordinate of the reference point of the suspension. The first coordinate can be a two-dimensional coordinate (x, y) or a three-dimensional coordinate (x, y, z). To improve the determination efficiency of the first motion parameter, it is preferably a two-dimensional coordinate. The following takes the two-dimensional coordinate as an example for illustration.

[0197] Then, based on the coordinates of the first feature point and the coordinates of the first reference point, determine the first distance D 1 ; and based on the coordinates of the first reference point and the coordinates of the interaction target point, determine the second distance D 2 .

[0198] Finally, the motion distance of the suspension can be determined according to the first coordinate and the first ratio between the second distance and the first distance

[0199] Among them, the first ratio, the first coordinate, and the preset suspension control coefficient are multiplied to obtain the motion distance of the suspension.

[0200] In an embodiment, the above first distance D 1 , the second distance D 2 can be calculated respectively through the following formulas:

[0201]

[0202] Among them, x 1 is the abscissa of the first feature point, x 2is the abscissa of the first reference point, x k is the abscissa of the interaction target point, y 1 is the ordinate of the first feature point, y 2 is the ordinate of the first reference point, y k is the ordinate of the interaction target point.

[0203] Furthermore, since the suspension mainly exhibits vertical movement, that is, the suspension mainly moves along the longitudinal axis, therefore, in order to improve efficiency, in one embodiment, the reference point of the suspension can be determined as the movement distance D based on the movement height of the aforementioned reset point g . The unit of this movement distance is meters. The following is a detailed description:

[0204] First, the first distance can be determined based on the ordinate of the first feature point and the ordinate of the first reference point. Exemplarily, the aforementioned first distance D 1 can be the absolute value of the difference between the ordinate y 1 of the first feature point and the ordinate y 2 of the first reference point: D 1 = |y 1 - y 2 |.

[0205] Then, the second distance can be determined based on the ordinate of the first reference point and the ordinate of the interaction target point. Exemplarily, the second distance can be the absolute value of the difference between the ordinate y k of the interaction target point and the ordinate y 2 of the first reference point: D 2 = |y k - y 2 |.

[0206] Then, the movement height of the reference point of the suspension based on the aforementioned reset point can be determined according to the product of the first coordinate (x 0 , y 0 ) and the first ratio between the aforementioned first distance and the second distance .

[0207] Exemplarily, this movement height can be obtained by multiplying the ordinate y 0 in the first coordinate by the first ratio

[0208] the aforementioned preset suspension control coefficient (k). Exemplarily, k = 0.1.

[0209] The above movement height can indicate the height of the reference point after movement, that is, the height of the suspension.

[0210] Then, when the movement distance is the movement height, in one embodiment, it can be calculated by the following formula:

[0211]

[0212] Among them, D g is the movement distance, k is a preset suspension control coefficient, y 0 is the ordinate of the first coordinate, D 1 is the first distance, D 2 is the second distance. Among them, D g , y 0 have the same unit, for example, they can both be in meters.

[0213] Alternatively, in one embodiment, it can be calculated by the following formula:

[0214]

[0215] Among them, D g is the movement distance, h max is the extreme height of the reference point, k is a preset suspension control coefficient, D 1 is the first distance, D 2 is the second distance. Among them, D g , h max have the same unit, for example, they can both be in meters.

[0216] Alternatively, in one embodiment, the above movement distance can be calculated by the following formula:

[0217]

[0218] Among them, D g is the movement distance, h max is the extreme height of the reference point, k is a preset suspension control coefficient, y 0 is the ordinate of the first coordinate, D 1 is the first distance, D 2 is the second distance. D g , h max , y 0 have the same unit, for example, they can both be in meters.

[0219] The extreme height h max of the above reference point can be a pre-specified height value. For example, it can be 0.05 meters.

[0220] It can be understood that h max in the above formula is the maximum height change value that the reference point can reach when the reference point moves away from the reset point in the direction perpendicular to the ground.

[0221] Furthermore, the first motion parameter of the suspension further includes a motion direction type to facilitate the determination of the motion direction of the suspension. Taking the reference point as the first feature point and the first reference point as an example, the determination of the motion direction type in the first motion parameter is described as follows:

[0222] Determine the ordinate y in the second position information of the interaction target point k And the ordinate y of the first reference point 2 The difference (i.e., y k -y 2 ) is the first difference.

[0223] In response to the first difference being less than a preset first target threshold, that is, the first difference between the ordinate of the second position information and the ordinate of the first reference point is less than the first target threshold, determine that the motion direction type is the first direction type.

[0224] Alternatively, in response to the first difference being greater than or equal to the first target threshold, determine that the motion type is the second direction type. The first target threshold can be 0, for example.

[0225] Wherein, the first motion direction corresponding to the first direction type is opposite to the second motion direction corresponding to the second direction type.

[0226] It can be understood that the meaning of the opposite motion direction here is: with the vehicle in a stationary state, before receiving the interaction instruction, taking the reset point of the suspension that coincides with the reference point of the suspension as the reference, the motion directions of the suspension are opposite.

[0227] In this way, if it is determined that the motion type is the first direction type, the suspension moves above the aforementioned reset point, that is, the position of the suspension after movement is above the horizontal line where the reset point is located.

[0228] If it is determined that the motion type is the second direction type, the suspension moves below the aforementioned reset point, that is, the position of the suspension after movement is below the horizontal line where the reset point is located.

[0229] For example, the first target threshold can be 0, then the first motion direction corresponding to the first direction type can be: the reference point of the suspension moves away from the aforementioned reset point towards the top of the vehicle, and the air spring corresponding to the suspension stretches; while the second motion direction corresponding to the second direction type is: the reference point of the suspension moves away from the aforementioned reset point towards the wheel direction (i.e., the ground direction), and the air spring corresponding to the suspension stretches.

[0230] To further improve the accuracy of the motion distance in the aforementioned first motion parameter, thereby improving the response stability of the suspension, taking the first motion parameter including the motion distance and the motion direction type as an example, the determination of the motion distance is described as follows:

[0231] First, after determining the type of motion direction based on the relative magnitude relationship between the vertical coordinate in the second position information of the interaction target point and the vertical coordinate of the first reference point, determine the fourth distance corresponding to the type of motion direction.

[0232] For example, when the type of motion direction is the first type of motion direction, determine the distance between the first feature point and the first reference point as the fourth distance.

[0233] When the type of motion direction is the second type of motion direction, determine the distance between the first reference point and the second feature point as the fourth distance. This second feature point corresponds to the bottom area of the user's posture. Please continue to refer to Figure 3 .

[0234] Then, based on the vertical coordinate of the first reference point and the vertical coordinate of the interaction target point, determine the second distance. And determine the ratio between the second distance and the fourth distance as the second ratio. In this way, obtain the second ratio corresponding to the type of motion direction.

[0235] Finally, based on this second ratio, the extreme height corresponding to the type of motion direction, and a preset suspension control coefficient, determine the motion distance.

[0236] When determining the motion distance in the above embodiments, by combining the type of motion direction, the type of motion direction in the first motion parameter is matched with the motion distance, so as to further improve the response stability of the suspension when moving in different directions.

[0237] Still taking the motion distance as the motion height D g as an example, one embodiment is provided and described as follows:

[0238] In response to the type of motion direction being the first type of motion direction, determine the fourth distance D 4 =|y 1 -y 2 |.

[0239] Alternatively, in response to the type of motion direction being the second type of motion direction, determine the fourth distance D 4 =|y 3 -y 2 |.

[0240] The second distance can still be calculated by D 2 =|y k -y 2 |. In this way, the motion height D g can be calculated according to the following expression:

[0241]

[0242] where D g is the motion distance corresponding to the type of motion direction, hmax is the extreme height corresponding to the type of movement direction, k is a preset suspension control coefficient, D 4 is the fourth distance corresponding to the type of movement direction, D 2 is the second distance. Then is the second ratio corresponding to the type of movement direction as described above.

[0243] Optionally, when the type of movement direction is the first direction type, the extreme height corresponding to the type of movement direction can be 0.07 meters.

[0244] When the type of movement direction is the second direction type, the extreme height corresponding to the type of movement direction is 0.05 meters.

[0245] Furthermore, when determining the user in the acquired image, especially for determining the user in the first acquired image among N acquired images, the following provides two embodiments for illustration:

[0246] Embodiment 1

[0247] First, the detection frame and the marking information of the detection frame in the image can be directly determined through the target detection algorithm. The marking information may include, for example, the position information of the detection frame, the type of the target in the detection frame, and the confidence of the type of the target. Among them, each detection frame uniquely corresponds to 1 target. Exemplarily, the type of the target can be distinguished by a type identifier, such as 001, 002, etc. The confidence of the type of the target represents the possibility that the target detection algorithm identifies the target as the type corresponding to the output type identifier. For example, if the confidence is expressed as a percentage, the larger the value of the percentage, the higher the possibility that the target corresponds to its type.

[0248] Then, according to the marking information of the detection frame, select the detection frame whose target type corresponds to the user and whose confidence meets the category threshold as the target detection frame.

[0249] Next, based on the preset pose information contained in the interaction instruction, determine the first similarity between the first pose information of the target in the target detection frame and the preset pose information to verify the user, so as to avoid misidentification of the user. If the first similarity is greater than the preset first similarity threshold, it can be determined that the target in the detection frame is the user. Otherwise, it is determined that the target in the detection frame is not the user.

[0250] Embodiment 2

[0251] First, the target detection frame in the image can be determined through the target detection algorithm, and then, continue to enhance the facial area of the user in the target detection frame to obtain a high-resolution facial image, realizing the high-definition restoration of the user's facial image.

[0252] Next, retrieve the pre-stored authorized user facial images. Determine the second similarity between the pre-stored authorized user facial images and the high-resolution facial images obtained through the aforementioned enhancement process. If the second similarity is greater than the preset second similarity threshold, it can be determined that the target in the detection box is the user. Otherwise, it is determined that the target in the detection box is not the user.

[0253] Furthermore, when determining the user in the aforementioned captured image (e.g., the first captured image), the detection box information of the captured image containing the user and the motion information of the user can also be obtained. Among them, the detection box information at least includes the position of the user in the image. The motion information at least includes the motion direction of the user. The motion direction can be determined by taking static objects in the captured image or the image coordinate system as a reference.

[0254] In the embodiments of the present application, the control of the suspension is achieved through human-vehicle interaction. To further improve the accuracy of the determined user and the position information of the user key points, so as to improve the response stability of the suspension, in one embodiment, in the same frame of captured image, by matching the detection boxes containing the user obtained by different algorithms, the purpose of verification is achieved, avoiding the problem that it is difficult to detect false detections due to incorrect user recognition in some captured images among N frames of captured images and correct user recognition in some captured images.

[0255] Specifically, first, in the captured image, the first detection box containing the user can be determined by matching the first type of detection box obtained by target detection and the second type of detection box obtained by trajectory prediction. Then each captured image contains the first type of detection box and the second type of detection box corresponding to the user obtained by different detection algorithms. If the first type of detection box and the second type of detection box match successfully, it can be determined that the first type of detection box is the first detection box containing the user.

[0256] Then, in the first detection box in the captured image, the key points and the position information of the key points of the user are determined. Specifically, when determining the key points of the user, the captured image containing the first detection box, or the captured image containing the first detection box and the detection box information of the first detection box can be input into the pre-trained key point detection algorithm together to obtain the key points and the position information of the key points of the user.

[0257] The pre-trained key point detection algorithm may include, but is not limited to, CPM (Convolutional Pose Machines) and / or YOLO-Pose (You Only Look Once Pose, YOLO human pose estimation algorithm).

[0258] In this embodiment, for the same frame of captured image, prediction is achieved by matching different types of detection boxes obtained by using two types of algorithms, and the purpose of verifying the targets obtained by prediction and detection is achieved, thereby improving the accuracy of the tracked user during the interaction between the user and the vehicle. Especially in an open scenario where the user is outside the vehicle, interference targets (such as passers-by) are likely to appear near the user. The method in this embodiment can significantly improve the accuracy of the tracked user by avoiding misidentification of the user, thereby improving the suspension response stability and effectively enhancing the user experience.

[0259] Optionally, when determining the first detection box containing the user in the captured image, if the aforementioned first type of detection box fails to match the second type of detection box, it can be considered that the user leaves at the time corresponding to the captured image, the interaction is interrupted, and the suspension control ends.

[0260] Preferably, to avoid the generation of incorrect first type of detection box or second type of detection box; or, during the target tracking process, the target is lost, resulting in the failure to generate the first type of detection box and / or the second type of detection box, causing the failure of the first type of detection box to match the second type of detection box. In one embodiment, in response to the matching parameter between the first type of detection box and the second type of detection box in the nth frame of captured image being less than a preset first matching parameter threshold, based on the first type of detection box in the (n - 1)th frame of captured image, the first detection box of the user in the nth frame of captured image is determined.

[0261] Among them, the matching parameter can be obtained by using the Hungarian algorithm to match the first type of detection box and the second type of detection box based on IOU (Intersection Over Union). Then there are only two values for the matching parameter: one indicates successful matching, and the other indicates failed matching.

[0262] Among them, the matching parameter corresponding to successful matching is greater than the first matching parameter threshold, and the matching parameter corresponding to failed matching is less than the first matching parameter threshold.

[0263] Exemplarily, if the aforementioned matching parameter is less than the first matching parameter threshold, according to the position information of the first type of detection box in the (n - 1)th frame of captured image, in the nth frame of captured image, any detection box with a confidence level or any target category at the position corresponding to the position information of the first type of detection box in the (n - 1)th frame of captured image is determined as the first detection box.

[0264] Exemplarily, if the foregoing matching parameter is less than the first matching parameter threshold, first, based on the position information of the first type of detection box containing the user in the captured image of the (n - 1)-th frame, determine whether there is an unmatched first type of detection box at the corresponding position in the captured image of the n-th frame. If not, directly use the detection box information of the first detection box in the captured image of the (n - 1)-th frame as the detection box information of the first detection box in the captured image of the n-th frame.

[0265] If so, determine whether the number of unmatched detection boxes at the corresponding position in the captured image of the n-th frame is 1. If so, determine the unmatched first type of detection box as the first detection box in the captured image of the n-th frame.

[0266] If not, the unmatched first type of detection box satisfies one of the following conditions: the target type in the detection box information does not match the user; the target type in the detection box information matches the user, but the confidence level of the target type corresponding to the user in the detection box information is lower than the threshold. Thus, the following rules can be used to select the first detection box containing the user from the unmatched first type of detection boxes:

[0267] Rule 1: If the unmatched first type of detection boxes include the first type of detection boxes with the target type matching the user, among the first type of detection boxes with the target type matching the user, determine the first type of detection box with the maximum confidence level as the first detection box.

[0268] Rule 2: If, in the detection box information of the unmatched first type of detection boxes, the target types all do not match the user, it can be determined that the target loss is caused by misidentification of the target, and then the first type of detection box with the minimum confidence level can be determined as the first detection box.

[0269] Further, the determination of the first detection box containing the user is described in detail below. Please refer to Figure 5 :

[0270] Step 501, perform target detection on the captured image to obtain the first type of detection box.

[0271] Among them, the first type of detection box includes: the second detection box in the captured image of the (n - 1)-th frame and the third detection box in the captured image of the n-th frame. n is an integer, and 2 ≤ n ≤ N.

[0272] Specifically, the number of the first type of detection boxes contained in each captured image can be 1 or greater than 1. And the number of the first type of detection boxes contained in each captured image can be equal or not equal.

[0273] In step 501, while obtaining the first type of detection box, the detection box information of the first type of detection box can also be generated. The detection box information includes at least one of the target category, confidence level, and position information of the target in the first type of detection box.

[0274] The first type of detection box corresponds one-to-one with the detection box information.

[0275] In one embodiment, the first type of detection box can be obtained by performing object detection on each acquired image through a pre-trained object detection algorithm.

[0276] In one embodiment, the object detection algorithm includes but is not limited to at least one of R-CNN (Regions with Convolutional Neural Networks), Mask R-CNN (Mask Region-based Convolutional Neural Networks), YOLO (You Only Look Once), SSD (Single Shot MultiBox Detector), FSSD (Feature-fused Single Shot Multibox Detector), and Efficient Det (Efficient Object Detection).

[0277] In this way, through the aforementioned object detection algorithm, when detecting the (n - 1)-th frame of the acquired image, the first type of detection box that conforms to the first detection rule can be marked as the second detection box.

[0278] Similarly, through the aforementioned object detection algorithm, when detecting the n-th frame of the acquired image, the first type of detection box that conforms to the first detection rule can be marked as the third detection box.

[0279] Among them, the first detection rule at least includes: in the detection box information of the first detection box, the target category matches the user, and the confidence level is greater than the corresponding confidence threshold.

[0280] Step 502: Predict the trajectory of the user in the (n - 1)-th frame of the acquired image to obtain the third information of the fourth detection box in the n-th frame of the acquired image.

[0281] Specifically, according to the motion information of the user in the second detection box in the (n - 1)-th frame of the acquired image, the trajectory of the user in the second detection box can be predicted to obtain the third information of the fourth detection box in the n-th frame of the acquired image.

[0282] Among them, the motion information includes the motion direction and / or speed of the user.

[0283] When predicting the trajectory, a preset trajectory prediction algorithm can be used. The trajectory prediction algorithm includes, but is not limited to, at least one of the Kalman filter algorithm, the particle filter algorithm, and the LSTM (Long Short Term Memory) network.

[0284] Thus, the fourth detection box is obtained by prediction and may be a second type of detection box that may contain the user in the nth frame of the captured image.

[0285] The aforementioned third detection box is obtained by object detection and may be a first type of detection box that may contain the user in the nth frame of the captured image.

[0286] For each frame of the captured image after the first frame of the captured image, the detection box information of the user in this frame of the captured image can be predicted based on the motion information of the user in the first type of detection box in the previous m frames of the captured image. The aforementioned detection box information includes at least the position information of the detection box.

[0287] Where 1 ≤ m ≤ n and m is an integer.

[0288] Step 503: For the nth frame of the captured image, in response to the matching parameter between the third detection box and the fourth detection box being less than a preset second matching parameter threshold, based on the second detection box, correct the third detection box in the nth frame of the captured image to obtain the first detection box.

[0289] Specifically, the matching parameter indicates the matching degree between the third detection box and the fourth detection box.

[0290] The above matching parameter includes, but is not limited to, at least one of IOU, Euclidean distance, cosine distance, and Mahalanobis distance.

[0291] In one embodiment, the above matching parameter can be obtained by using a matching algorithm such as the pre-specified Hungarian algorithm in combination with IOU to match the third detection box and the fourth detection box.

[0292] If the matching parameter is less than the preset second matching parameter threshold, it indicates that the matching between the third detection box and the fourth detection box fails. When the matching parameter is less than the preset second matching parameter threshold, it indicates that the target is lost, occluded, or the user is still in the nth frame of the captured image but is misidentified as another target.

[0293] Therefore, the detection result of the nth frame of the captured image can be corrected. Specifically, the information of the third detection box can be corrected according to the information of the second detection box, and the first detection box is generated as the detection box of the user in the nth frame of the captured image.

[0294] In one embodiment, based directly on the information of the second detection box in the image acquired in the (n - 1)-th frame, a detection box at the same position is determined as the first detection box in the image acquired in the n-th frame.

[0295] To further improve the accuracy of user recognition and enhance the response stability of the suspension, in one embodiment, during the execution of step 502: Before determining the first detection box of the user in the image acquired in the n-th frame, the first-type detection boxes and second-type detection boxes in the image acquired in the (n - 1)-th frame can be verified first. That is, first, through steps 501 - 503, the first-type detection box containing the user is determined in the image acquired in the (n - 1)-th frame, realizing the verification of the second detection box, so as to obtain the first detection box in the image acquired in the (n - 1)-th frame.

[0296] Then, based on the motion information of the target in the first detection box in the image acquired in the (n - 1)-th frame, trajectory prediction is performed to obtain the fourth detection box in the image acquired in the n-th frame.

[0297] And so on, the trajectory prediction of each frame of the acquired image is predicted according to the motion information of the user (i.e., the motion information of the target in the first detection box) in the previous acquired image containing the user, so as to improve the accuracy of the trajectory prediction in each acquired image by improving the accuracy of the fourth detection box.

[0298] To further improve the accuracy of user recognition and enhance the response stability of the suspension, in one embodiment, when the matching parameter is less than the preset second matching parameter threshold, the misdetection or target loss caused by detection jitter or jump in the current acquired image can be recognized first. Specifically, in response to the matching parameter being less than the preset second matching parameter threshold, the third detection box can be corrected by the following method:

[0299] First, based on the time stamps carried by each frame of the acquired image among N frames of the acquired image, the first number of acquired images before the n-th frame of the acquired image is determined as the target image sequence.

[0300] Then, in response to all the acquired images in the target image sequence including the first detection box, that is, each acquired image in the target image sequence contains a detection box, it can be determined that the n-th frame of the acquired image has a misdetection or loss. Then, it is determined to correct the third detection box: Based on the second detection box, the third detection box in the n-th frame of the acquired image is corrected to obtain the first detection box.

[0301] Or, in response to the number of acquired images containing the first detection box in the target image sequence being less than the preset second number, there is no user in this frame of the acquired image, and it is determined that the suspension control ends.

[0302] In one embodiment, after the foregoing step 502, it further includes:

[0303] In response to the foregoing matching parameter being greater than or equal to the foregoing second matching parameter threshold, determine the third detection box in the nth frame of the acquired image as the first detection box.

[0304] In one embodiment, when determining the first detection box and the third detection box, the information of the first detection box and the information of the second detection box are also determined simultaneously.

[0305] Among them, the information of the first detection box includes the identifier of the target in this detection box: the first identifier. The information of the third detection box includes the identifier of the target in this detection box: the third identifier. At this time, the identifiers of the targets in the first detection box and the third detection box are different, and when determining the third detection box as the first detection box, it is actually determined that the target in the third detection box and the target in the first detection box are the same target. Thus, in one embodiment, after determining the third detection box as the first detection box, the third identifier of the third detection box can be modified to the first identifier of the user in the first detection box.

[0306] Then, the identifiers of the targets in each detection box can be different. For example, the identifier of the user in the first detection box is different from the target in the second detection box. Also, for example, the target in the second detection box is different from the target in the third detection box. The target in the third detection box is also different from the target in the fourth detection box.

[0307] Further, after determining the first detection box in the N frames of the acquired image, based on this first detection box, the foregoing key points and key point position information can be determined:

[0308] First, the pre-trained first detection algorithm can be used to process the N frames of the acquired image one by one: based on the information of the first detection box, in the acquired image, the feature information of the foregoing pose points is determined.

[0309] Then, according to the foregoing category information of the pose points, the reference point and the interaction target point are determined, and the reference point is processed based on the preset rules to obtain the first feature point and the second feature point; then the key points and the key point position information are obtained.

[0310] To improve the efficiency and accuracy of determining the key point position information and save the computing power of the terminal, in one embodiment, the ordinate of the foregoing key points can be directly determined.

[0311] Exemplarily, the interaction target point corresponding to the hand can also be determined according to the category information of the pose points.

[0312] Exemplarily, according to the category information of the pose points, a third reference point corresponding to the elbow and a fourth reference point corresponding to the wrist are selected from the pose points. Then, the third reference point and the fourth reference point are connected, and the target length is extended in the direction from the third reference point to the fourth reference point to obtain a fifth reference point. The extended target length is the product of the distance between the third reference point and the fourth reference point and a third coefficient. For example, the third coefficient can be 0.3. Then, the fifth reference point obtained by extension can be determined as the interaction target point.

[0313] To further improve the recognition accuracy of the interaction target point, in one embodiment, the target distance between the fourth reference point corresponding to the wrist and the fifth reference point can be determined first according to the foregoing category information. In response to the target distance being less than a preset fourth threshold, the fifth reference point corresponding to the hand is determined as the interaction target point.

[0314] Exemplarily, the target distance D o can be obtained by the following method: after calculating the sum of squares of the coordinate differences between the fourth reference point corresponding to the wrist and the fifth reference point, calculate the arithmetic square root. For example, the coordinates of the fourth reference point are (x t , y t ), and the coordinates of the fifth reference point are (x 6 , y 6 ).

[0315]

[0316] Thus, in one embodiment, to determine the first motion parameter for controlling the suspension, the reference point and the interaction target point corresponding to the user's hand can be determined first in the acquired image.

[0317] Then, the second reference point and the first reference point in the reference points are processed through a preset rule to obtain a reference point.

[0318] Finally, the first motion parameter can be determined based on the relative position relationship between the interaction target point and the reference point, and the pose information of the hand.

[0319] Optionally, when the pose information remains the first gesture type, the motion direction type and / or the motion distance in the first motion parameter can be directly determined based on the above relative position relationship.

[0320] Optionally, the pose information can include a second gesture type and a third gesture type. Then, the motion direction type and / or the motion distance can be determined based on the above relative position relationship; and, based on the second gesture type or the third gesture type, the motion rate type in the first motion parameter can be determined.

[0321] For example, the above first gesture type, second gesture type, and third gesture type can each independently be selected from a fist gesture, a like gesture, an "OK" gesture, etc.

[0322] For example, the motion speed type includes a first speed type and a second speed type. Then, the suspension motion speed corresponding to the first speed type is greater than the suspension motion speed corresponding to the second speed type.

[0323] Then, when determining the motion speed type, it can be determined according to a preset correspondence relationship between the gesture type and the motion speed type:

[0324] The preset correspondence relationship includes the correspondence relationship between the second gesture type and the first speed type, and the correspondence relationship between the third gesture type and the second speed type. Then, the control of the suspension motion speed can be achieved according to the changes of different gesture types.

[0325] In summary, in the suspension control method provided by the embodiments of the present application, please refer to Figure 6 , and through an interaction instruction, determine to interact with the user to control the suspension to move in the direction perpendicular to the ground (the longitudinal axis direction). Specifically, first determine the interaction object (user) in the N-frame captured images: determine the identifier of the interaction object. Thereafter, track the interaction object in the frame captured images: determine the user with the same identifier in each frame, and this identifier corresponds one-to-one to the target detection box where the user is located.

[0326] Then, the first motion parameter of the suspension can be determined according to the change in the ordinate of the user's interaction target point in each frame of the captured image: perform mapping according to the ratio between the ordinate of the interaction target point and the distance between the ordinates of two reference points to obtain the first motion parameter of the suspension. In this way, the suspension motion is adaptively controlled through the continuous coordinate changes of the user's interaction target point; thereby effectively improving the response stability of the suspension.

[0327] Furthermore, the following further gives examples of the suspension control method provided by the embodiments of the present application as follows:

[0328] When the user needs to interact with the vehicle, the user approaches the vehicle to unlock the vehicle. Specifically, the user can start the suspension control through a mobile terminal to send an interaction instruction to the vehicle through the mobile terminal.

[0329] After the vehicle receives the interaction instruction, according to the user information contained in the interaction instruction (such as the user's location information, etc.), determine the camera for capturing the aforementioned captured images, and the capture parameters of the camera. The capture parameters include but are not limited to the shooting magnification, etc.

[0330] After obtaining the captured image through the above camera, the captured image containing the user can be determined according to the shooting mode selected by the user in the interactive instruction. For example, the shooting mode can be day mode, and the target in the detection frame with the largest area in the captured image is determined as a possible user.

[0331] For another example, if the shooting mode is a custom mode, and the custom mode includes a start-up posture selected by the user, then the target whose posture in the captured image is the start-up posture is a possible user.

[0332] The above shooting mode may also include a lighting mode, whereby the vehicle may turn on the lights to create a lighting stage. In the captured image, the target located within the light projection area may be determined as a possible user.

[0333] The target detection frame of the possible user may be further enlarged by 1.5 times, the face may be identified, and the face area may be cropped.

[0334] The facial area is enhanced to obtain a high-resolution face. Specifically, the cropped facial area can be first encoded using the encoder on the vehicle side and then uploaded to the cloud to save local computing resources. The decoder on the cloud side is used for enhancement processing to achieve high-definition face restoration and the high-resolution face is transmitted back to the vehicle side.

[0335] The facial set of authorized users pre-stored on the vehicle side is compared with the high-resolution face sent back from the cloud. If the comparison is successful in the facial set, the possible user is determined to be the user who sent the interaction instruction. In this way, the comparison on the vehicle side can improve the security of user information.

[0336] After the user is identified, the user's posture may be verified. If the user's posture is a pre-specified human posture, the verification is successful. The captured image where the user is located may be determined as the first frame of the captured image.

[0337] Then, the control of the suspension can be started from the posture of the user in the first frame of the captured image. Then the posture of the user in each captured image after the first frame of the captured image is used to control the suspension. For this reason, the user can also be tracked from the first frame of the captured image, thereby avoiding the problems of reduced efficiency and delayed suspension response caused by using the aforementioned method of user face recognition for each frame of the captured image.

[0338] In this way, for each frame of the captured images of the second frame, the third frame, ..., the Nth frame, the first type of detection boxes obtained by the object detection algorithm and the second type of detection boxes obtained by the trajectory prediction algorithm are matched in the same captured image to achieve user tracking and avoid the problem of incorrect user recognition. If the matching fails in a certain frame of the captured image, the user information of the first number of captured images before this frame of the captured image is obtained as the position information and pose information of the user in the current frame of the captured image, thereby avoiding the problem of user loss caused by jitter and target jump that are likely to occur in the object detection process.

[0339] Based on this, in the first frame of the captured image and the subsequent captured images, the reference point of the user and the hand for determining the interaction target point can be further identified. The detection algorithm used for this identification can specifically be the yolo-pose algorithm.

[0340] Next, the first feature point and / or the second feature point can be determined by using the identified second reference point corresponding to the shoulder and the first reference point corresponding to the waist. Specifically, in the vertical direction, the height between the first reference point corresponding to the waist and the second reference point corresponding to the shoulder is determined as H, and then the ordinate of the second reference point corresponding to the shoulder is added with 1.6H to obtain the ordinate of the first feature point. That is, the first preset rule in the foregoing preset rules is used to process the first reference point and the second reference point to obtain the ordinate of the first feature point. This first feature point can be the highest point of the preset pose: the highest point that the hand of a user in a standing pose can reach.

[0341] Moreover, the ordinate of the first reference point corresponding to the waist is subtracted by 0.3H to determine the ordinate of the second feature point. That is, the second preset rule in the foregoing preset rules is used to process the first reference point and the second reference point to obtain the ordinate of the second feature point.

[0342] Continue to determine the interaction target point: The interaction target point can be obtained by directly positioning (i.e., detecting) the user's hand. Alternatively, the reference point corresponding to the elbow and the reference point corresponding to the wrist are used. The coordinates of the palm center, that is, the coordinates of the interaction target point, are obtained by adding 0.3 times the distance between the reference point corresponding to the elbow and the reference point corresponding to the wrist to the abscissa and ordinate of the reference point corresponding to the wrist respectively.

[0343] In this way, according to the first ratio between the second distance between the ordinate of the interaction target point and the ordinate of the first human key point, that is, the second distance between the center point of the palm and the first key point corresponding to the waist, and the first distance, the movement distance of the suspension is mapped to adjust the height of the suspension.

[0344] Meanwhile, the movement direction type of the suspension can also be determined based on the relative magnitude relationship between the ordinate of the center point of the user's palm and the ordinate of the first reference point corresponding to the waist; that is, in the direction perpendicular to the ground, moving upward or downward along the direction away from the reset line.

[0345] In this way, the suspension can be made to move dynamically up and down following the user's interaction target point in each captured image, achieving the purpose of efficient and stable response, and effectively improving the user experience.

[0346] It should be understood that although Figure 1 、 Figure 5 、 Figure 6 the steps in the flowchart are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 、 Figure 5 、 Figure 6 at least a part of the steps in

[0347] Based on the same inventive concept, as Figure 7 shown, an embodiment of the present application provides a suspension control device, including: an instruction module 701, a parameter module 702, and a motion module 703, where:

[0348] The instruction module 701 is configured to, in response to receiving an interaction instruction, acquire a captured image and determine the key point position information of the user in the captured image; wherein, the key point position information includes the first position information of the reference point and the second position information of the interaction target point.

[0349] The parameter module 702 is configured to determine a first motion parameter of the suspension based on the relative position relationship between the reference point and the interaction target point.

[0350] The motion module 703 is configured to control the movement of the suspension based on the first motion parameter.

[0351] In one embodiment, the instruction module 701 can be used to determine the key points and the key point position information.

[0352] In one embodiment, the instruction module 701 is specifically configured to:

[0353] In the acquired image, a first detection box containing the user is determined by matching the first type of detection box obtained by object detection with the second type of detection box obtained by trajectory prediction; in the first detection box of the acquired image, the key points of the user and the position information of the key points are determined.

[0354] In one embodiment, the instruction module 701 may specifically be configured to: perform object detection on the acquired image to obtain the first type of detection box; wherein, the first type of detection box includes the second detection box in the (n - 1)-th frame of the acquired image and the third detection box in the n-th frame of the acquired image, n is an integer, and 2 ≤ n ≤ N; predict the trajectory of the user in the second detection box in the (n - 1)-th frame of the acquired image to obtain the fourth detection box in the n-th frame of the acquired image; for the n-th frame of the acquired image, in response to the matching parameter between the third detection box and the fourth detection box being less than a preset second matching parameter threshold, based on the second detection box, correct the third detection box in the n-th frame of the acquired image to obtain the first detection box.

[0355] In one embodiment, the instruction module 701 is specifically configured to:

[0356] Based on the time stamp carried by the acquired image, determine a first number of the acquired images before the n-th frame of the acquired image as a target image sequence; in response to the acquired images in the target image sequence including the first detection box, correct the third detection box in the n-th frame of the acquired image to obtain the first detection box.

[0357] In one embodiment, the instruction module 701 is further configured to:

[0358] In response to the matching parameter between the third detection box and the fourth detection box being greater than or equal to the second matching parameter threshold, determine the third detection box of the n-th frame of the acquired image as the first detection box.

[0359] In one embodiment, the instruction module 701 may specifically be configured to:

[0360] In response to the matching parameter between the first type of detection box and the second type of detection box in the n-th frame of the acquired image being less than a preset first matching parameter threshold, based on the first type of detection box in the (n - 1)-th frame of the acquired image, determine the first detection box of the user in the n-th frame of the acquired image.

[0361] In one embodiment, the instruction module 701 may further be configured to:

[0362] Based on the information of the first detection frame, determine the feature information of the pose points in the acquired image; wherein, the feature information includes the category information of the pose points; according to the category information of the pose points, determine the reference point and the interaction target point; then obtain the key points and the key point position information.

[0363] In one embodiment, the parameter module 702 may specifically be used for:

[0364] Based on the first position information and the second position information, determine the relative position relationship between the reference point and the interaction target point; based on the relative position relationship, determine the first motion parameter of the suspension.

[0365] In one embodiment, the parameter module 702 may specifically be used for:

[0366] Based on the ordinate of the first feature point and the ordinate of the first reference point, determine the first distance; based on the ordinate of the first reference point and the ordinate of the interaction target point, determine the second distance.

[0367] In one embodiment, the parameter module 702 is specifically used for:

[0368] Determine the motion distance of the suspension according to the product of the ordinate of the first coordinate and the first ratio.

[0369] In one embodiment, the motion distance is determined according to the following formula:

[0370] where D g is the motion distance, h max is the extreme height of the reference point, k is a preset suspension control coefficient, y 0 is the ordinate of the first coordinate, D 1 is the first distance, D 2 is the second distance.

[0371] In one embodiment, the parameter module 702 is specifically used for:

[0372] Based on the relative position relationship, determine the second motion parameter of the reference point of the suspension; wherein, the interaction target point corresponds to the reference point of the suspension; determine the second motion parameter as the first motion parameter.

[0373] In one embodiment, the reference point includes a first feature point in the top region corresponding to the user's pose and a first reference point in the middle region corresponding to the user's pose; the first motion parameter includes the motion distance of the suspension; then the parameter module 702 is specifically used for:

[0374] Obtain the first coordinates of the reference point of the suspension; determine a first distance based on the coordinates of the first feature point and the coordinates of the first reference point, and determine a second distance based on the coordinates of the first reference point and the coordinates of the interaction target point; determine the movement distance of the suspension according to the first coordinates and a first ratio between the second distance and the first distance.

[0375] In one embodiment, the reference point includes a first feature point indicating the highest point of the user's posture and a first reference point indicating the midpoint of the user's posture; the first motion parameter includes the type of the movement direction of the suspension; then the parameter module 702 is further configured to:

[0376] In response to a first difference between the ordinate of the second position information and the ordinate of the first reference point being less than a preset first target threshold, determine that the type of the movement direction is a first direction type; or, in response to the first difference being greater than or equal to the first target threshold, determine that the type of the movement direction is a second direction type; wherein, a first direction corresponding to the first direction type is opposite to a second direction corresponding to the second direction type.

[0377] For the specific definition of the suspension control device, reference may be made to the definition of the suspension control method in the foregoing text, which will not be elaborated herein. Each module in the foregoing suspension control device can be implemented in whole or in part by software, hardware, and their combination. The foregoing modules can be embedded in the processor in the electronic device in the form of hardware or be independent of the processor, or can be stored in the memory in the electronic device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to the foregoing modules.

[0378] Based on the same inventive concept, please refer to Figure 8 , an embodiment of the present application further provides an electronic device. In one embodiment, as shown in the figure, the electronic device may include a memory 801, a communication module 803, and one or more processors 802.

[0379] The memory 801 is used to store a computer program executed by the processor 802. The memory 801 may mainly include a program storage area and a data storage area. Among them, the program storage area may store an operating system; the data storage area may store various operation instruction sets, etc.

[0380] The memory 801 can be a volatile memory, such as a random-access memory (RAM); the memory 801 can also be a non-volatile memory, such as a read-only memory, a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD); or the memory 801 is any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 801 can be a combination of the above memories.

[0381] The processor 802 can include one or more central processing units (CPUs) or be a digital processing unit, etc. The processor 802 is used to implement the above-mentioned suspension control method when calling the computer program stored in the memory 801.

[0382] The communication module 803 is used to communicate with a terminal device, a site device or other network devices.

[0383] In the embodiments of the present application, the specific connection medium between the above-mentioned memory 801, communication module 803 and processor 802 is not limited. In the embodiments of the present application Figure 8 it is described that the memory 801 and the processor 802 are connected through a bus 804. The bus 804 is described in thick lines in Figure 8 The connection manners between other components are only for illustrative purposes and are not limited thereto. The bus 804 can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of description, Figure 8 only a thick line is used to describe it in

[0384] The memory 801 stores a computer storage medium, and the computer storage medium stores computer-executable instructions for implementing the method for determining suspension control in the embodiments of the present application. The processor 802 is used to execute the suspension control methods in the various embodiments of the above-mentioned computer-executable instructions.

[0385] In one embodiment, when the computer-executable instructions are executed by the processor, the following steps are further implemented:

[0386] In response to receiving an interaction instruction, acquire a captured image, and determine the key point position information of the user in the captured image; wherein, the key point position information includes the first position information of a reference point and the second position information of an interaction target point; based on the relative position relationship between the reference point and the interaction target point, determine a first motion parameter of the suspension; based on the first motion parameter, control the motion of the suspension.

[0387] In one embodiment, when the computer-executable instructions are executed by a processor, the following steps are further implemented:

[0388] Determine key points and key point position information corresponding to the key points.

[0389] In one embodiment, when the computer-executable instructions are executed by a processor, the following steps are further implemented:

[0390] Based on the first position information and the second position information, determine the relative position relationship between the reference point and the interaction target point; based on the relative position relationship, determine a first motion parameter of the suspension.

[0391] In one embodiment, when the computer-executable instructions are executed by a processor, the following steps are further implemented:

[0392] Based on the ordinate of the first feature point and the ordinate of the first reference point, determine the first distance; based on the ordinate of the first reference point and the ordinate of the interaction target point, determine the second distance.

[0393] In one embodiment, when the computer-executable instructions are executed by a processor, the following steps are further implemented:

[0394] Determine the motion distance of the suspension according to the product of the ordinate of the first coordinate and the first ratio.

[0395] In one embodiment, when the computer-executable instructions are executed by a processor, the following steps are further implemented:

[0396] In response to the matching parameter between the first type of detection frame and the second type of detection frame in the nth frame of the captured image being less than a preset first matching parameter threshold, based on the first type of detection frame in the (n - 1)th frame of the captured image, determine the first detection frame of the user in the nth frame of the captured image.

[0397] In one embodiment, when the computer-executable instructions are executed by a processor, the following steps are further implemented:

[0398] The reference points include a first feature point within the top region corresponding to the user posture and a first reference point within the middle region corresponding to the user posture; the first motion parameter includes the motion distance of the suspension; obtain the first coordinate of the reference point of the suspension; determine a first distance based on the coordinates of the first feature point and the coordinates of the first reference point, and determine a second distance based on the coordinates of the first reference point and the coordinates of the interaction target point; determine the motion distance of the suspension according to the first coordinate and a first ratio between the second distance and the first distance.

[0399] In one embodiment, when the computer-executable instructions are executed by a processor, the following steps are further implemented:

[0400] The reference points include a first feature point indicating the highest point of the user posture and a first reference point indicating the midpoint of the user posture; the first motion parameter includes the type of motion direction of the suspension; in response to a first difference between the ordinate of the second position information and the ordinate of the first reference point being less than a preset first target threshold, determine that the type of motion direction is a first direction type; or, in response to the first difference being greater than or equal to the first target threshold, determine that the type of motion direction is a second direction type; wherein, a first direction corresponding to the first direction type is opposite to a second direction corresponding to the second direction type.

[0401] In one embodiment, when the computer-executable instructions are executed by a processor, the following steps are further implemented:

[0402] In the acquired image, determine a first detection frame containing the user by matching a first type of detection frame obtained by target detection with a second type of detection frame obtained by trajectory prediction; in the first detection frame of the acquired image, determine the key points of the user and the key point position information.

[0403] In one embodiment, when the computer-executable instructions are executed by a processor, the following steps are further implemented:

[0404] Perform target detection on the acquired image to obtain the first type of detection frame; wherein, the first type of detection frame includes a second detection frame in the (n - 1)th frame of the acquired image and a third detection frame in the nth frame of the acquired image, n is an integer, and 2 ≤ n ≤ N; predict the trajectory of the user in the second detection frame in the (n - 1)th frame of the acquired image to obtain a fourth detection frame in the nth frame of the acquired image; for the nth frame of the acquired image, in response to a matching parameter between the third detection frame and the fourth detection frame being less than a preset second matching parameter threshold, correct the third detection frame in the nth frame of the acquired image based on the second detection frame to obtain the first detection frame.

[0405] In one embodiment, when the computer-executable instructions are executed by a processor, the following steps are further implemented:

[0406] Based on the time stamp carried by the acquired image, determine a first number of the acquired images before the nth acquired image as a target image sequence; in response to the acquired images in the target image sequence including the first detection frame, correct the third detection frame in the nth acquired image to obtain the first detection frame.

[0407] In one embodiment, when the computer-executable instructions are executed by a processor, the following steps are further implemented:

[0408] In response to the matching parameter between the third detection frame and the fourth detection frame being greater than or equal to the second matching parameter threshold, determine the third detection frame of the nth acquired image as the first detection frame.

[0409] In one embodiment, when the computer-executable instructions are executed by a processor, the following steps are further implemented:

[0410] Based on the information of the first detection frame, determine the feature information of the pose points in the acquired image; wherein, the feature information includes the category information of the pose points; according to the category information of the pose points, determine the reference point and the interaction target point; then obtain the key points and the key point position information.

[0411] In one embodiment, when the computer-executable instructions are executed by a processor, the following steps are further implemented:

[0412] The key point position information is the ordinate of the key point; then the first position information is the ordinate of the reference point, and the second position information is the ordinate of the interaction target point.

[0413] Those skilled in the art can understand that Figure 8 the structure shown in is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the electronic device to which the solution of the present application is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0414] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0415] In response to receiving an interaction instruction, acquire an acquired image, and determine the key point position information of the user in the acquired image; wherein, the key point position information includes the first position information of the reference point and the second position information of the interaction target point;

[0416] Determine a first motion parameter of the suspension based on a relative positional relationship between the reference point and the interaction target point.

[0417] Control the movement of the suspension based on the first motion parameter.

[0418] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0419] Determine key point position information of the key points.

[0420] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0421] Determine a relative positional relationship between the reference point and the interaction target point based on the first position information and the second position information; determine a first motion parameter of the suspension based on the relative positional relationship.

[0422] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0423] Determine the first distance based on the ordinate of the first feature point and the ordinate of the first reference point; determine the second distance based on the ordinate of the first reference point and the ordinate of the interaction target point.

[0424] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0425] Determine a movement distance of the suspension according to a product of the ordinate of the first coordinate and a first ratio between the first distance and the second distance.

[0426] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0427] In response to a matching parameter between the first type detection frame and the second type detection frame in the nth frame captured image being less than a preset first matching parameter threshold, determine the first detection frame of the user in the nth frame captured image based on the first type detection frame in the (n - 1)th frame captured image.

[0428] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0429] The reference points include a first feature point within the top region corresponding to the user's posture and a first reference point within the middle region corresponding to the user's posture; the first motion parameter includes the motion distance of the suspension; obtain the first coordinates of the reference point of the suspension; determine a first distance based on the coordinates of the first feature point and the coordinates of the first reference point, and determine a second distance based on the coordinates of the first reference point and the coordinates of the interaction target point; determine the motion distance of the suspension according to the first coordinates and a first ratio between the second distance and the first distance.

[0430] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0431] The reference points include a first feature point indicating the highest point of the user's posture and a first reference point indicating the midpoint of the user's posture; the first motion parameter includes the type of motion direction of the suspension; in response to a first difference between the ordinate of the second position information and the ordinate of the first reference point being less than a preset first target threshold, determine that the type of motion direction is a first direction type; or, in response to the first difference being greater than or equal to the first target threshold, determine that the type of motion direction is a second direction type; wherein, a first direction corresponding to the first direction type is opposite to a second direction corresponding to the second direction type.

[0432] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0433] In the N captured images, determine a first detection frame containing the user by matching a first type of detection frame obtained by target detection and a second type of detection frame obtained by trajectory prediction; N is an integer greater than or equal to 2, and in the first detection frame of the captured image, determine the key points of the user and the key point position information.

[0434] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0435] Perform target detection on the captured image to obtain the first type of detection frame; wherein, the first type of detection frame includes a second detection frame in the (n - 1)th frame of the captured image and a third detection frame in the nth frame of the captured image, n is an integer, and 2 ≤ n ≤ N; predict the trajectory of the user in the second detection frame in the (n - 1)th frame of the captured image to obtain a fourth detection frame in the nth frame of the captured image; for the nth frame of the captured image, in response to a matching parameter between the third detection frame and the fourth detection frame being less than a preset second matching parameter threshold, correct the third detection frame in the nth frame of the captured image based on the second detection frame to obtain the first detection frame.

[0436] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0437] Based on the time stamp carried by the acquired image, determine a first number of the acquired images before the nth acquired image as a target image sequence; in response to the acquired images in the target image sequence including the first detection box, correct the third detection box in the nth acquired image to obtain the first detection box.

[0438] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0439] In response to the matching parameter between the third detection box and the fourth detection box being greater than or equal to the second matching parameter threshold, determine the third detection box of the nth acquired image as the first detection box.

[0440] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0441] Based on the information of the first detection box, determine the feature information of the pose points in the acquired image; wherein, the feature information includes the category information of the pose points; according to the category information of the pose points, determine the reference point and the interaction target point; then obtain the key points and the key point position information.

[0442] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0443] Based on the same inventive concept, an embodiment of the present application further provides a computer program product, including a computer program, which when executed by a processor, implements the suspension control method described in any one of the above.

[0444] Among them, the program code for implementing the computer program product of the present application can be written in any combination of one or more programming languages, and the program code can be executed entirely on a user device, partially on a user device, executed as an independent software package, partially on a user device and partially on a remote device, or entirely on a remote device.

[0445] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0446] The present application is described with reference to the flowcharts and / or block diagrams of the method, device (system), and computer program product according to the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0447] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured product including an instruction device, and the instruction device implements the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0448] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of user operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide for implementing the processFigure 1 one process or multiple processes and / or boxes Figure 1 steps of functions specified in one box or multiple boxes.

[0449] The embodiments described above merely represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the appended claims.

Claims

1. A suspension control method, characterized in that: include: In response to receiving the interaction instruction, acquiring a captured image, and determining key point position information of the user in the captured image; wherein the key point position information includes first position information of a reference point and second position information of an interaction target point; determining a first motion parameter of the suspension based on a relative position relationship between the reference point and the interaction target point; Based on the first motion parameter, the suspension motion is controlled.

2. The method according to claim 1, characterized in that The determining of the first motion parameter of the suspension based on the relative position relationship between the reference point and the interaction target point includes: Based on the relative position relationship, determining a second motion parameter of the interactive target point; wherein the interactive target point corresponds to a reference point of the suspension, and the second motion parameter includes a motion distance and / or a motion direction type; Based on the second motion parameter, the first motion parameter is determined.

3. The method according to claim 1 or 2, characterized in that The reference points include a first reference point corresponding to a middle area of ​​the user's gesture; The determining of the first motion parameter of the suspension based on the relative position relationship between the reference point and the interaction target point includes: The first motion parameter is determined based on a relative position relationship between the first reference point and the interaction target point.

4. The method according to claim 3, characterized in that The first motion parameter includes the motion distance of the suspension; The determining of the first motion parameter of the suspension based on the relative position relationship between the reference point and the interaction target point includes: Acquire a first coordinate of a reference point of the suspension; Determining a first distance based on coordinates of a first feature point and coordinates of the first reference point, and determining a second distance based on coordinates of the first reference point and coordinates of the interaction target point; wherein the first feature point corresponds to a top area of ​​the user gesture; The movement distance of the suspension is determined according to the first coordinate and a first ratio between the second distance and the first distance.

5. The method according to claim 4, characterized in that The reference points include a second reference point corresponding to a shoulder region of the user posture; The first feature point is obtained by processing the first reference point and the second reference point according to a first preset rule.

6. The method according to claim 4, characterized in that The determining of the first distance based on the coordinates of the first feature point and the coordinates of the first reference point, and the determining of the second distance based on the coordinates of the first reference point and the coordinates of the interaction target point, comprises: determining the first distance based on the ordinate of the first feature point and the ordinate of the first reference point; The second distance is determined based on the longitudinal coordinate of the first reference point and the longitudinal coordinate of the interaction target point.

7. The method according to claim 6, characterized in that Determining the movement distance of the suspension according to the first coordinate and a first ratio between the second distance and the first distance includes: The movement distance of the suspension is determined according to the product of the ordinate of the first coordinate, a preset suspension control coefficient and the first ratio.

8. The method according to claim 3, characterized in that The first motion parameter includes a motion direction type of the suspension; The determining of the first motion parameter of the suspension based on the relative position relationship between the reference point and the interaction target point includes: In response to a first difference between the ordinate in the second position information and the ordinate of the first reference point being less than a preset first target threshold, determining that the motion direction type is a first direction type; or, In response to the first difference being greater than or equal to the first target threshold, determining the motion direction type as a second direction type; The first direction corresponding to the first direction type is opposite to the second direction corresponding to the second direction type.

9. The method according to claim 8, characterized in that The movement distance in the first movement parameter is determined by the following method: determining a fourth distance corresponding to the type of movement direction, and an extreme height of the suspension corresponding to the type of movement direction; Determine a second distance; wherein the second distance is the distance between the first reference point and the interaction target point; Determine a ratio of the second distance to the fourth distance as a second ratio; wherein the second ratio corresponds to the motion direction type; The movement distance is determined based on the second ratio and the extreme height corresponding to the movement direction type.

10. The method according to claim 9, characterized in that Determining a fourth distance corresponding to the motion direction type includes: In response to the motion direction type being the first direction type, determining the distance between the first feature point and the first reference point as the fourth distance; or, In response to the motion direction type being the second direction type, determining the distance between the first reference point and the second feature point as the fourth distance; wherein the second feature point corresponds to the bottom area of ​​the user gesture, The second feature point is obtained by processing the second reference point and the first reference point according to a second preset rule.

11. The method according to claim 10, characterized in that The determining of the first motion parameter of the suspension based on the relative position relationship between the reference point and the interaction target point includes: In the captured image, determining the reference point and the interactive target point corresponding to the user's hand; wherein the reference point includes the first reference point and the second reference point; The first motion parameter is determined based on the relative position relationship between the interaction target point and the first reference point, the second reference point, and the posture information of the hand.

12. The method according to claim 1, characterized in that The determining key point position information of the user in the captured image includes: In the N frames of the collected images, a first detection frame containing the user is determined by matching a first type detection frame obtained by target detection with a second type detection frame obtained by trajectory prediction; wherein N is an integer greater than or equal to 2; In the first detection frame of the captured image, key points of the user and position information of the key points are determined.

13. The method according to claim 12, characterized in that Determining a first detection frame containing the user by matching a first type detection frame obtained by target detection with a second type detection frame obtained by trajectory prediction in the collected image includes: In response to a matching parameter between the first type detection frame and the second type detection frame in the nth frame of captured image being less than a preset first matching parameter threshold, the first detection frame of the user in the nth frame of captured image is determined based on the first type detection frame in the (n-1)th frame of captured image; wherein n is an integer and 2≤n≤N.

14. The method according to claim 12, characterized in that Determining a first detection frame containing the user by matching a first type detection frame obtained by target detection with a second type detection frame obtained by trajectory prediction in the collected image includes: Performing target detection on the collected image to obtain the first type of detection frame; wherein the first type of detection frame includes the second detection frame in the (n-1)th frame of collected image and the third detection frame in the nth frame of collected image, where n is an integer and 2≤n≤N; Predicting the trajectory of the user in the second detection frame in the (n-1)th frame of captured image to obtain a fourth detection frame of the user in the nth frame of captured image; For the n-th frame acquisition image, in response to the matching parameter between the third detection frame and the fourth detection frame being less than a preset second matching parameter threshold, based on the second detection frame, the third detection frame in the n-th frame acquisition image is corrected to obtain the first detection frame.

15. The method according to claim 14, characterized in that The step of correcting the third detection frame in the nth frame of acquired image based on the second detection frame to obtain the first detection frame includes: Based on the time stamps carried by the acquired images, determining a first number of the acquired images before the nth acquired image as a target image sequence; In response to the collected image in the target image sequence including the first detection frame, the third detection frame in the n-th frame collected image is corrected to obtain the first detection frame.

16. The method according to claim 14, characterized in that After predicting the trajectory of the user in the second detection frame in the (n-1)th frame of the acquired image to obtain the fourth detection frame in the nth frame of the acquired image, the method further includes: In response to the matching parameter between the third detection frame and the fourth detection frame being greater than or equal to the second matching parameter threshold, the third detection frame of the n-th frame acquisition image is determined to be the first detection frame.

17. The method according to claim 12, characterized in that Determining the key points of the user and the key point position information in the first detection frame of the captured image includes: Based on the information of the first detection frame, determining feature information of the posture point in the collected image; wherein the feature information includes category information of the posture point; According to the category information of the posture point, the reference point and the interactive target point are determined; and the key point and key point position information are obtained.

18. A suspension control device, characterized in that: include: An instruction module, configured to acquire a captured image in response to receiving an interaction instruction, and determine key point position information of the user in the captured image; wherein the key point position information includes first position information of a reference point and second position information of an interaction target point; a parameter module, configured to determine a first motion parameter of the suspension based on a relative position relationship between the reference point and the interaction target point; A motion module is used to control the suspension motion based on the first motion parameter.

19. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 17 are implemented.

20. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 17 are implemented.

Images