Suspension control method, electronic equipment and storage medium

Abstract

The invention provides a suspension control method, electronic equipment and a storage medium, which can lock a target user in a target area of a vehicle, identify the user action of the target user when determining that the state of the target user is normal, and control a suspension of the vehicle according to the user action. Namely, the suspension of the vehicle can be controlled through the recognized user action of the target user, interactivity between the vehicle and the user is improved, the target user needs to be locked before action recognition, the state of the target user is determined to be normal, interference caused by other users when multiple users exist in an application scene can be prevented, and user experience is improved. And the suspension control accuracy is improved.

Description

Technical Field

[0001] The present application relates to the technical field of suspension control, and in particular to a suspension control method, electronic equipment and storage medium. Background Art

[0002] In the current era of rapid development of intelligent cars, car suspensions need to interact with users. The current human-suspension interaction technology usually involves the vehicle suspension automatically adjusting after the APP is started. For example: after the APP is started, the vehicle suspension automatically adjusts to achieve a "dancing" visual effect. In other words, after the APP is started, the vehicle suspension shakes freely to achieve the effect of shaking off the leaves on the car. However, the existing suspension interaction scenes are more of an effect display. The user only operates a start button throughout the process, and there is no subsequent "interaction". Only watching is left, the interactivity is not strong, and the user experience is poor. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide a suspension control method, an electronic device and a storage medium to solve the above technical problems.

[0004] In one aspect, a suspension control method is provided, comprising:

[0005] Locate the target user within the target area of ​​the vehicle;

[0006] When it is determined that the state of the target user is normal, identifying a user action of the target user;

[0007] A suspension of the vehicle is controlled according to the user action.

[0008] In one embodiment, locking a target user in a target area of ​​a vehicle includes:

[0009] Capturing an image of a target area of ​​the vehicle, and when determining based on the captured image that a user in the target area performs a target action, locking the user as a target user;

[0010] or,

[0011] Capturing an image of a target area of ​​the vehicle, and when determining, based on the captured image, that a facial feature of a user in the target area meets a preset facial feature, locking the user as a target user;

[0012] or,

[0013] An image is captured of a target area of ​​the vehicle, and when it is determined based on the captured image that a user in the target area performs a target action, and when it is determined based on the image that the facial features of the user meet preset facial features, the user is locked as a target user.

[0014] In one of the embodiments, determining that the status of the target user is normal includes:

[0015] When it is determined that the target user has not left the target area, determining that the state of the target user is normal;

[0016] or,

[0017] When it is determined that the target user has not left the target area, and when it is determined that the distance between the target user and the vehicle is within a preset distance range, it is determined that the state of the target user is normal.

[0018] In one embodiment, determining that the target user has not left the target area includes:

[0019] When the target user is locked, images of the target area are captured at preset time intervals, and an image counter is started to record the number of captured image frames;

[0020] When the target user is identified in the captured n-th frame image, it is determined that the target user has not left the target area, and image capture of the target area continues, and the image counter is cleared and counted again.

[0021] In one embodiment, identifying the user action of the target user includes:

[0022] After the image counter is cleared and counted again, the user gesture action of the target user is recognized according to the re-captured image.

[0023] In one embodiment, the identifying the user gesture action of the target user according to the re-captured image includes:

[0024] Taking the continuous m frames of the re-captured images as an image set, and respectively identifying the user gesture actions of the target user in each of the images in the image set;

[0025] The controlling the suspension of the vehicle according to the user action comprises:

[0026] When the user gesture actions in each of the images in the image set match a preset gesture action in a preset gesture action set, the suspension of the vehicle is controlled to execute a suspension control instruction corresponding to the preset gesture action.

[0027] In one embodiment, the image set includes a first image set and a second image set, the first image set is a set consisting of re-captured images from the 1st frame to the mth frame, and the second image set is a set consisting of re-captured images from the m+1th frame to the 2mth frame;

[0028] When the user gesture actions in each of the images in the image set match a preset gesture action in a preset gesture action set, controlling the suspension of the vehicle to execute a suspension control instruction corresponding to the preset gesture action includes:

[0029] When the user gesture actions of each of the images in the first image set match a first preset gesture action in a preset gesture action set, controlling the suspension of the vehicle to enter an initialization preparation state;

[0030] When the suspension is in the initialization preparation state, if the user gesture actions of each of the images in the second image set match the second preset gesture actions in the gesture action set, the suspension of the vehicle is controlled to execute the suspension control instructions corresponding to the second preset gesture actions.

[0031] In one embodiment, determining the user gesture action of the target user according to the re-captured image includes:

[0032] Determining, according to the hand position of the target user in the recaptured image of the first frame and the image of the mth frame, whether the user gesture action of the target user is an upward gesture or a downward gesture;

[0033] The controlling the suspension of the vehicle according to the user action comprises:

[0034] When the user gesture is an upward gesture, controlling at least one suspension of the vehicle to rise;

[0035] When the user gesture action is a descending gesture action, at least one suspension of the vehicle is controlled to descend.

[0036] Furthermore, an electronic device is provided, comprising a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program to implement any of the above methods.

[0037] Furthermore, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by at least one processor, it implements any of the methods described above.

[0038] Through the suspension control method, electronic device and storage medium provided by the present application, a target user can be locked in a target area of ​​a vehicle. When it is determined that the target user is in a normal state, the user action of the target user is identified, and the suspension of the vehicle is controlled according to the user action. That is, the suspension of the vehicle can be controlled by the user action of the identified target user, thereby improving the interactivity between the vehicle and the user. Because the target user needs to be locked and the target user is determined to be in a normal state before action recognition, interference caused by other users can be prevented when there are multiple users in the application scenario, thereby improving the accuracy of suspension control. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A schematic flow chart of a suspension control method provided in Embodiment 1 of the present application;

[0040] Figure 2 A schematic flow chart of a suspension control method provided in Embodiment 2 of the present application;

[0041] Figure 3 This is a schematic diagram of the structure of an electronic device provided in Example 3 of the present application. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is 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.

[0043] The present application embodiment provides a suspension control method, see Figure 1 As shown, the following steps are included:

[0044] S101: Locking a target user in a target area of ​​a vehicle.

[0045] S102: When it is determined that the state of the target user is normal, identifying a user action of the target user.

[0046] S103: Controlling the suspension of the vehicle according to the user action.

[0047] The above steps are described in detail below.

[0048] In the embodiment of the present application, the target area can be an area outside the vehicle or an area inside the vehicle. For example, the target area can be an image acquisition area outside the vehicle, and the vehicle can capture images of the image acquisition area through a camera, and then lock the target user based on the captured images.

[0049] For step S101, in a first optional implementation, images may be collected for a target area of ​​the vehicle, and when a user in the target area is determined to perform a target action based on the collected images, the user is locked as a target user.

[0050] In this embodiment, the target action can be an action preset by the vehicle owner, or an action preset and stored in the vehicle before the vehicle leaves the factory. The target action includes but is not limited to at least one of a gesture action, a body action, and an expression action. For example, the target action can be a hand-raising action.

[0051] For step S101, in a second optional implementation, an image may be captured for a target area of ​​the vehicle, and when it is determined based on the captured image that facial features of a user in the target area meet preset facial features, the user is locked as a target user.

[0052] In this embodiment, the preset facial features can be pre-stored in the vehicle by the user. For example, the vehicle can pre-collect the facial features of the owner user and store the facial features in the vehicle. If the facial features of a user in the target area are determined to meet the facial features based on the collected image, it means that the user is the owner user, and the user is locked as the target user.

[0053] For step S101, in a third optional implementation, images may be captured of a target area of ​​the vehicle, and when it is determined based on the captured images that a user in the target area performs a target action, and when it is determined based on the images that the facial features of the user meet preset facial features, the user is locked as a target user.

[0054] The suspension control method provided in the embodiment of the present application requires pre-locking the target user to prevent interference from other users. During the suspension control process, since the target user has been locked, the recognition of the actions of other non-related users can be avoided, thereby improving the efficiency of image recognition.

[0055] For step S102, determining that the state of the target user is normal is to ensure that the action of the target user can be accurately identified.

[0056] Therefore, for step S102, in an optional implementation, when it is determined that the target user has not left the target area, it can be determined that the state of the target user is normal. In another optional implementation, when it is determined that the target user has not left the target area, and when it is determined that the distance between the target user and the vehicle is within a preset distance range, it can be determined that the state of the target user is normal. The target user has not left the target area, and the distance between the target user and the vehicle is within the preset distance range, indicating that the vehicle can accurately identify the target user's actions. After ensuring that the target user's actions can be accurately identified, the target user's actions are identified, which can improve the success rate of the target user's action recognition and ensure that each recognition operation can obtain the corresponding user action.

[0057] It can be understood that in an embodiment of the present application, when it is determined that the state of the target user is abnormal, the recognition of the target user's user actions can be suspended. After ensuring that the state of the target user is normal, the target user's actions can be further recognized to avoid the situation where the target user's actions cannot be accurately recognized due to the abnormal state of the target user.

[0058] In the embodiment of the present application, it is possible to determine whether the target user has left the target area by image recognition, which may include:

[0059] When locking the target user, the target area is imaged at preset time intervals, and an image counter is started to record the number of image frames captured; when the target user is identified in the nth frame of the captured image, it is determined that the target user has not left the target area, and image capture of the target area continues, and the image counter is cleared and counted again.

[0060] It should be noted that the specific value of n in the embodiment of the present application can be flexibly set by the developer, for example, it can be set to 15.

[0061] When determining whether the target user has left the target area, there is no need to analyze every frame of the captured image. Instead, only the last frame of the image in a capture cycle can be analyzed. This can improve the image recognition efficiency and further improve the processing efficiency of the entire process.

[0062] It can be understood that the user action in step S102 includes but is not limited to at least one of a user gesture action, a user expression action and a user body action.

[0063] Specifically, in step S102, after the image counter is cleared and counted again, the user gesture action of the target user can be identified according to the re-captured image, and in step S103, the suspension of the vehicle can be controlled according to the user gesture action.

[0064] It should be noted that when identifying the user gesture of the target user based on the captured image, the gesture analysis may be performed on each frame of the captured image, or only on part of the frames.

[0065] In a first example, identifying the user gesture action of the target user based on the recaptured image includes: taking the continuous m frames of the image in the recaptured image as an image set, and identifying the user gesture action of the target user in each of the images in the image set respectively.

[0066] The controlling of the suspension of the vehicle according to the user action includes: when the user gesture actions in each of the images in the image set match a preset gesture action in a preset gesture action set, controlling the suspension of the vehicle to execute a suspension control instruction corresponding to the preset gesture action.

[0067] It should be noted that the specific value of m can be flexibly set by the developer, for example, it can be set to 3. Preferably, the value of m is the same as the value of n.

[0068] In this example, for each frame of the image in the image set, the user gesture action of the target user needs to be analyzed. Only when the user gesture actions in each image in the image set match a preset gesture action in the preset gesture action set, the vehicle's suspension is controlled to execute the suspension control instruction corresponding to the preset gesture action, thereby ensuring the accuracy of the suspension control.

[0069] Each preset gesture action in the preset gesture action set has its corresponding suspension control instruction. The specific preset gesture actions and specific suspension control instructions support user customization and can also be pre-set in the vehicle before the vehicle leaves the factory.

[0070] The preset gesture actions in this example include but are not limited to at least one of a fist gesture, an OK gesture, and a thumbs-up gesture, and the suspension control instructions include but are not limited to at least one of an instruction for pausing suspension adjustment, an instruction for confirming suspension adjustment, and an instruction for ending suspension adjustment.

[0071] For example, when the preset gesture action set includes a fist gesture, and the suspension control instruction corresponding to the fist gesture is an instruction for pausing suspension adjustment, then for each frame of the image set, if the user gesture actions in each image match the fist gesture, the suspension adjustment is controlled to be suspended.

[0072] In this example, when it is ensured that the user gesture action of each frame image in the image set matches a preset gesture action, the suspension is controlled to execute the control instruction corresponding to the preset gesture action, which can prevent the target user from accidentally triggering irrelevant suspension control instructions.

[0073] In the second example, determining the user gesture action of the target user based on the re-captured image includes: determining whether the user gesture of the target user is an upward gesture or a downward gesture based on the hand position of the target user in the re-captured image of the 1st frame and the image of the mth frame; controlling the suspension of the vehicle based on the user action includes: when the user gesture action is an upward gesture action, controlling at least one suspension of the vehicle to rise; when the user gesture action is a downward gesture action, controlling at least one suspension of the vehicle to descend.

[0074] Exemplarily, when the user gesture is a left hand raising gesture, the left front suspension and / or left rear suspension of the vehicle is controlled to rise; when the user gesture is a left hand lowering gesture, the left front suspension and / or left rear suspension of the vehicle is controlled to lower; when the user gesture is a right hand raising gesture, the right front suspension and / or right rear suspension of the vehicle is controlled to rise; when the user gesture is a right hand lowering gesture, the right front suspension and / or right rear suspension of the vehicle is controlled to lower.

[0075] Exemplarily, when the user gesture is a left hand raising gesture or a right hand raising gesture, the four suspensions of the vehicle are controlled to rise; when the user gesture is a left hand lowering gesture or a right hand lowering gesture, the four suspensions of the vehicle are controlled to fall.

[0076] Exemplarily, when the user's gesture is a left hand raising gesture + a right palm facing outward gesture, the left front suspension of the vehicle is controlled to rise; when the user's gesture is a left hand raising gesture + a right palm facing inward gesture, the left rear suspension of the vehicle is controlled to rise; when the user's gesture is a left hand lowering gesture + a right palm facing outward gesture, the left front suspension of the vehicle is controlled to lower; when the user's gesture is a left hand lowering gesture + a right palm facing inward gesture, the left rear suspension of the vehicle is controlled to lower; for the control of the right suspension, you can refer to the control method of the left suspension here, and I will not go into details here.

[0077] In this example, for the continuous m frames of the re-captured images, only the 1st frame image and the mth frame image may be analyzed. Specifically, the hand position of the target user in the 1st frame image and the mth frame image may be analyzed, and the hand movement direction and distance may be determined based on the hand position, thereby determining whether the user gesture action of the target user is an upward gesture or a downward gesture.

[0078] For dynamic gestures such as the raising gesture and the lowering gesture, we only need to pay attention to the hand positions in the first and last frames. Therefore, there is no need to perform recognition and analysis on the intermediate image frames, which can improve image recognition efficiency and thus improve control efficiency.

[0079] In some embodiments, the height of the vehicle suspension rise can also be determined according to the distance the hand is raised, and similarly, the height of the vehicle suspension drop can be determined according to the distance the hand is lowered. For example, the height of the vehicle suspension rise or drop can be determined according to the formula h1=a*h2, where h1 represents the height of the vehicle suspension rise or drop, h2 represents the distance the target user's hand is raised or lowered, and a is a preset scaling factor, which can be flexibly set by the developer, for example, it can be set to 1, or it can support user customization.

[0080] It should be noted that in actual application scenarios, the user's hand may shake within a small range, for example, it may shake upward in a small range, or shake downward in a small range. At this time, the user may not expect to control the suspension. In order to avoid miscontrol of the suspension caused by this situation, at this time, when it is determined that the user's gesture action is an upward gesture action and the lifting distance of the target user's hand is greater than the preset distance threshold, at least one suspension of the vehicle can be controlled to rise; similarly, when it is determined that the user's gesture action is a downward gesture action and the descending distance of the target user's hand is greater than the preset distance threshold, at least one suspension of the vehicle can be controlled to descend.

[0081] The distance of the hand being raised or lowered can be determined based on the hand position of the target user in the image of the first frame and the image of the mth frame.

[0082] If it is determined that the target user has not moved during the time corresponding to the m frames of images, the first frame of image and the m-th frame of image can be directly analyzed to determine the moving direction and distance of the target user's hand. Specifically, the coordinates of the target user's hand position in the first frame of image and the m-th frame of image are directly compared. If it is determined based on the coordinate comparison result that the hand position in the m-th frame of image is moved up relative to the hand position in the first frame of image, then the user gesture action of the target user is determined to be an upward gesture action. If it is determined based on the coordinate comparison result that the hand position in the m-th frame of image is lowered relative to the hand position in the first frame of image, then the user gesture action of the target user is determined to be a downward gesture action.

[0083] In one example, if it is determined that the target user moves within the time corresponding to the m frames of images, the gesture recognition process may be exited to ensure the accuracy of gesture recognition.

[0084] In another example, if it is determined that the target user moves within the time corresponding to the m frames of images, the first frame of image and / or the mth frame of image can be scaled to obtain a first processed image corresponding to the image of the first frame and a second processed image corresponding to the image of the mth frame, and the image areas corresponding to the target user in the first processed image and the second processed image are the same size. After aligning the image areas corresponding to the head of the target user in the first processed image and the second processed image, the coordinates of the hand position of the target user in the aligned first processed image and the second processed image are compared. If it is determined based on the coordinate comparison result that the hand position in the second processed image moves up relative to the hand position in the first processed image, then the user gesture action of the target user is determined to be an upward gesture action. If it is determined based on the coordinate comparison result that the hand position in the second processed image moves down relative to the hand position in the first processed image, then the user gesture action of the target user is determined to be a downward gesture action.

[0085] It should be noted that, in this example, the image of the first frame can be scaled based on the image of the mth frame as a reference, so that the image area size corresponding to the target user in the image of the first frame after the scaling process is the same as the image area size corresponding to the target user in the image of the mth frame. At this time, the image of the first frame after the scaling process is the first processed image, and the image of the mth frame is the second processed image. Similarly, the image of the first frame can be scaled based on the image of the first frame as a reference, so that the image area size corresponding to the target user in the image of the mth frame after the scaling process is the same as the image area size corresponding to the target user in the image of the first frame. At this time, the image of the mth frame after the scaling process is the second processed image, and the image of the first frame is the first processed image. It can be understood that the image of the first frame and the image of the mth frame can also be scaled separately, as long as the image area size corresponding to the target user in the image of the first frame after the scaling process is the same as the image area size corresponding to the target user in the image of the mth frame.

[0086] It should also be noted that the user action of the target user can be a static gesture or a dynamic gesture. Static gestures refer to gestures that are presented without moving the hand, such as the OK gesture and the thumbs-up gesture, while dynamic gestures refer to gestures that require moving the hand, such as the up gesture, the down gesture, and the hand-raising gesture.

[0087] When it is determined that the target user's status is normal, the target user's gesture action can be first determined based on the re-captured image whether it is a static gesture action or a dynamic gesture action. If it is a static gesture action, then for each frame image in the subsequently captured image set, its gesture action is analyzed to see whether it matches a preset static gesture action in the preset gesture action set. If it is a dynamic gesture, then for the subsequently captured image set, only the 1st frame image and the mth frame image need to be analyzed.

[0088] Specifically, for step S102 and step S103, it can be determined whether the user action of the target user is a static gesture action. If so, the user gesture action of the target user is analyzed for each frame of the image in the image set. Only when the user gesture actions in each image in the image set match a preset static gesture action in the preset gesture action set, the suspension of the vehicle is controlled to execute the suspension control instruction corresponding to the preset gesture action. If not, for the continuous m frames of the images in the re-captured images, only the hand position of the target user in the first frame and the mth frame is analyzed, and the hand movement direction and distance are determined according to the hand position, and then it is determined whether the user gesture action of the target user is an upward gesture or a downward gesture, thereby controlling the suspension to rise or fall.

[0089] In some embodiments, in order to prevent misoperation, the height of the suspension can be adjusted only when the suspension is in an initialized ready state. That is, when the suspension is in a non-initialized state, adjustment of the vehicle's suspension according to user actions can be prohibited.

[0090] Exemplarily, the image set includes a first image set and a second image set, the first image set is a set of recaptured images from the 1st frame to the mth frame, and the second image set is a set of recaptured images from the m+1th frame to the 2mth frame; when the user gesture action in each of the images in the image set matches a preset gesture action in a preset gesture action set, controlling the suspension of the vehicle to execute a suspension control instruction corresponding to the preset gesture action includes:

[0091] When the user gesture actions of each of the images in the first image set match a first preset gesture action in a preset gesture action set, controlling the suspension of the vehicle to enter an initialization preparation state;

[0092] When the suspension is in the initialization preparation state, if the user gesture actions of each of the images in the second image set match the second preset gesture actions in the gesture action set, the suspension of the vehicle is controlled to execute the suspension control instructions corresponding to the second preset gesture actions; of course, when the suspension is in the initialization preparation state, if the image of the 1st frame and the image of the mth frame in the second image set are analyzed and it is determined that the user gesture of the target user is an upward gesture or a downward gesture, the suspension of the vehicle is controlled to rise or fall.

[0093] Through the suspension control method provided in the embodiment of the present application, the target user can be locked in the target area of ​​the vehicle. When it is determined that the target user is in a normal state, the user action of the target user is identified, and the suspension of the vehicle is controlled according to the user action. That is, the suspension of the vehicle can be controlled by the user action of the identified target user, thereby improving the interactivity between the vehicle and the user. Because the target user needs to be locked and the target user is determined to be in a normal state before action recognition, interference caused by other users can be prevented when there are multiple users in the application scenario, thereby improving the accuracy of suspension control.

[0094] Embodiment 2:

[0095] For better understanding, the embodiment of the present application provides a more specific suspension control method. The user actions of the target user in the embodiment of the present application include but are not limited to OK gesture, lift gesture (also known as lifting gesture), lower gesture (also known as lowering gesture), fist gesture, and hand-raising gesture. Each gesture can trigger a corresponding control instruction, wherein the hand-raising gesture triggers the vehicle to lock the target user, the OK gesture triggers the vehicle's suspension to enter the initialization preparation state, the lift gesture triggers the vehicle's suspension to rise, the lower gesture triggers the vehicle's suspension to fall, the fist gesture triggers the suspension height adjustment to be paused, and the thumbs-up gesture triggers the suspension adjustment to end. The control process is explained in detail below:

[0096] For the user operation end, the following steps are included:

[0097] S11: Start the target application.

[0098] S12: The target user performs a hand-raising gesture.

[0099] S13: The target user performs an OK gesture.

[0100] S14: The target user raises / lowers his hand.

[0101] S15: The target user performs a fist gesture.

[0102] S16: The target user performs a like gesture.

[0103] When the target user triggers the start of the target application, the system side triggers S21: the main process starts.

[0104] After the main process is started, S31 is triggered: the pedestrian detection algorithm is started, and S41 is triggered: the gesture detection algorithm is started.

[0105] It is understandable that, for the system side, it is possible to determine whether the user performs a hand-raising gesture by performing image recognition on the target area.

[0106] Specifically, the system performs step S22: acquiring 15 frames of image data. The pedestrian detection algorithm performs step S32: judging whether the user raising his hand is detected according to the 15 frames of image data, if not, going to step S22, if yes, going to step S23.

[0107] The system executes step S23: acquiring the 15th frame of image data.

[0108] The pedestrian detection algorithm executes step S33: judging whether it is a specific user according to the 15th frame image data. Specifically, the facial features of the user who raised his hand can be compared with the preset facial features. If they are consistent, the user is locked as the target user. If they are inconsistent, step S34 is executed: ending the pedestrian detection process.

[0109] The system executes step S24: confirming that the state of the target user is correct; then executes step S25: continuing to acquire 15 frames of image data; then executes step S26: extracting the image data corresponding to the target user; triggering the gesture detection algorithm to execute step S42: starting gesture recognition.

[0110] Specifically, the gesture detection algorithm can perform the following steps in sequence:

[0111] S43: Detect OK gesture;

[0112] S44: Recognize that the hand height changes;

[0113] S45: detecting fist gesture;

[0114] S46: detecting a thumbs-up gesture;

[0115] S47: An invalid gesture is detected.

[0116] When an OK gesture is detected, the suspension adjustment end is triggered by the MCU to execute step S51: controlling the suspension to enter an initialization preparation state.

[0117] When it is recognized that the hand height changes, the suspension adjustment end is triggered by the MCU to execute step S52: controlling the suspension to rise / fall.

[0118] When a fist gesture is detected, the suspension adjustment end is triggered by the MCU to execute step S53: controlling the suspension adjustment to pause.

[0119] When a thumbs-up gesture or an invalid gesture is detected, the system is triggered to execute step S27: obtain an end signal; then execute step S34; then execute step S48: enter the end gesture recognition process; then execute step S54: reset the suspension; and execute step S28: end the target application.

[0120] In an embodiment of the present application, the user clicks the start button of the waving suspension in the APP, the main process of the system is started, and then the pedestrian detection algorithm sub-process is started, and the gesture detection algorithm sub-process is started.

[0121] User operation end: After the user starts the APP, the user needs to raise his hand to confirm that the user will be the target user for subsequent operations. Then, the target user makes an OK gesture with one hand, and the waving suspension function is officially started. The target user can then raise / lower his left hand, and the left suspension will rise / fall accordingly; or the target user can raise / lower his right hand, and the right suspension will rise / fall accordingly. When the target user raises / lowers both hands, the left and right suspensions rise or fall together.

[0122] During the target user's operation, the target user can make a fist gesture to suspend the adjustment of one side of the suspension. For example, when the left hand makes a fist gesture, the left suspension adjustment is suspended, and when the right hand makes a fist gesture, the right suspension adjustment is suspended. When the target user has finished the experience, he can make a thumbs-up gesture, at which time the suspension is reset and the function ends.

[0123] System algorithm side: The vehicle's camera can capture images of the target area outside the vehicle. Specifically, 15 frames of continuously captured image data can be transmitted to the system side. The pedestrian detection algorithm detects whether the target user has raised his hand based on the image data. If the hand-raising feature is not detected, the collected data is returned again. After the user's hand is detected, the algorithm locks the target user, and the target user can start gesture operation. The video device side continues to transmit 15 frames of image data. The pedestrian detection algorithm confirms that the target user is still within a specific range and continues to lock the target user. If the target user's status is confirmed to be correct, the system side will extract the target user's image data and hand it over to the gesture detection algorithm side to detect the gesture. If the target user's status fails to be determined, such as: the target user leaves the scene, the system directly enters the end process. The gesture recognition algorithm will process the cropped pedestrian data every 15 frames. If it is a valid gesture, the MCU is notified, and if it is an invalid gesture, a new round of detection will continue. When the thumbs-up gesture is detected, the two algorithm processes are terminated and the program ends.

[0124] Suspension adjustment end: When the MCU obtains the adjustment signal, it sends the relevant signal to the suspension to control the suspension adjustment. When the OK gesture is detected, the MCU notifies the suspension to prepare for initialization. When the height change of the user's gesture is detected, the suspension is notified to rise / fall. When the fist gesture is detected, the suspension adjustment is paused. When the MCU transmits the end signal, the suspension is reset and the adjustment ends.

[0125] It should be understood that, although the various steps in the above-mentioned flow chart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the above-mentioned flow chart may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0126] Embodiment three:

[0127] See also Figure 3 As shown, an embodiment of the present application provides an electronic device, including a processor 301 and a memory 302, wherein the memory 302 stores a computer program, and the processor 301 executes the computer program to implement the steps of the method introduced above, which will not be repeated here.

[0128] The processor 301 may be an integrated circuit chip with signal processing capabilities. The processor 301 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. It may implement or execute various methods, steps and logic block diagrams disclosed in the embodiments of the present application. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0129] The memory 302 may include, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable read-only memory (EPROM), electrically erasable read-only memory (EEPROM), etc.

[0130] This embodiment also provides a computer-readable storage medium, such as a floppy disk, a CD, a hard disk, a flash memory, a USB flash disk, an SD card, an MMC card, etc., in which one or more programs for implementing the above steps are stored. These one or more programs can be executed by one or more processors to implement the steps of the method in the above embodiment 1, which will not be repeated here.

[0131] It should be noted that the diagram provided in the present embodiment only illustrates the basic concept of the present invention in a schematic manner, so the diagram only shows the components related to the present invention rather than drawing according to the number, shape and size of the components during actual implementation. The type, quantity and ratio of each component during actual implementation can be a random change, and the component layout type may also be more complicated. The structure, ratio, size, etc. illustrated in the drawings of the present specification are only used to match the content disclosed in the specification for people familiar with this technology to understand and read, and are not used to limit the limiting conditions that the present invention can implement, so they have no technical substantive significance. Any modification of the structure, change of the proportional relationship or adjustment of the size should still fall within the scope of the technical content disclosed by the present invention without affecting the effect that the present invention can produce and the purpose that can be achieved. At the same time, the terms such as "upper", "lower", "left", "right", "middle" and "one" quoted in this specification are only for the convenience of narration, and are not used to limit the scope of the present invention. The change or adjustment of its relative relationship should also be regarded as the scope of the present invention without substantially changing the technical content.

[0132] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0133] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A suspension control method, characterized in that: include: Locate the target user within the target area of ​​the vehicle; When it is determined that the state of the target user is normal, identifying a user action of the target user; A suspension of the vehicle is controlled according to the user action.

2. The suspension control method according to claim 1, characterized in that: The step of locking a target user in a target area of ​​the vehicle includes: Capturing an image of a target area of ​​the vehicle, and when determining based on the captured image that a user in the target area performs a target action, locking the user as a target user; or, Capturing an image of a target area of ​​the vehicle, and when determining, based on the captured image, that a facial feature of a user in the target area meets a preset facial feature, locking the user as a target user; or, An image is captured of a target area of ​​the vehicle, and when it is determined based on the captured image that a user in the target area performs a target action, and when it is determined based on the image that the facial features of the user meet preset facial features, the user is locked as a target user.

3. The suspension control method according to claim 1, characterized in that: The determining that the status of the target user is normal includes: When it is determined that the target user has not left the target area, determining that the state of the target user is normal; or, When it is determined that the target user has not left the target area, and when it is determined that the distance between the target user and the vehicle is within a preset distance range, it is determined that the state of the target user is normal.

4. The suspension control method according to claim 3, characterized in that: The determining that the target user has not left the target area includes: When the target user is locked, images of the target area are captured at preset time intervals, and an image counter is started to record the number of captured image frames; When the target user is identified in the captured n-th frame image, it is determined that the target user has not left the target area, and image capture of the target area continues, and the image counter is cleared and counted again.

5. The suspension control method according to claim 4, characterized in that: The identifying the user action of the target user includes: After the image counter is cleared and counted again, the user gesture action of the target user is recognized according to the re-captured image.

6. The suspension control method according to claim 5, characterized in that: The identifying the user gesture action of the target user according to the re-collected image includes: Taking the continuous m frames of the re-captured images as an image set, and respectively identifying the user gesture actions of the target user in each of the images in the image set; The controlling the suspension of the vehicle according to the user action comprises: When the user gesture actions in each of the images in the image set match a preset gesture action in a preset gesture action set, the suspension of the vehicle is controlled to execute a suspension control instruction corresponding to the preset gesture action.

7. The suspension control method according to claim 6, characterized in that: The image set includes a first image set and a second image set, the first image set is a set consisting of re-captured images from the 1st frame to the mth frame, and the second image set is a set consisting of re-captured images from the m+1th frame to the 2mth frame; When the user gesture actions in each of the images in the image set match a preset gesture action in a preset gesture action set, controlling the suspension of the vehicle to execute a suspension control instruction corresponding to the preset gesture action includes: When the user gesture actions of each of the images in the first image set match a first preset gesture action in a preset gesture action set, controlling the suspension of the vehicle to enter an initialization preparation state; When the suspension is in the initialization preparation state, if the user gesture actions of each of the images in the second image set match the second preset gesture actions in the gesture action set, the suspension of the vehicle is controlled to execute the suspension control instructions corresponding to the second preset gesture actions.

8. The suspension control method according to claim 5, characterized in that: The determining the user gesture action of the target user according to the re-collected image includes: Determining, according to the hand position of the target user in the recaptured image of the first frame and the image of the mth frame, whether the user gesture action of the target user is an upward gesture or a downward gesture; The controlling the suspension of the vehicle according to the user action comprises: When the user gesture is an upward gesture, controlling at least one suspension of the vehicle to rise; When the user gesture action is a descending gesture action, at least one suspension of the vehicle is controlled to descend.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein a computer program is stored in the memory, and the processor executes the computer program to implement the method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by at least one processor, the method according to any one of claims 1 to 8 is implemented.

Images