Noise reduction method of automobile headrest and automobile headrest

Abstract

The invention discloses a noise reduction method of an automobile headrest and the automobile headrest, and relates to the technical field of headrests. Noise reduction modules are arranged on the headrest body and the headrest side wings, so that the noise reduction range is enlarged. A passenger head portrait corresponding to the automobile headrest is collected, and spatial position information and posture angle information of the passenger head relative to the headrest side wings and the headrest body are obtained through analysis and processing. The calculated amount is small, and the requirement for hardware is low. The position information of the headrest side wings and the headrest body where the passenger is located is determined according to the space position information and the posture angle information, so that the noise reduction module and the ears of the passenger are kept at stable relative positions, and subsequent adjustment of the headrest posture adjusting mechanism is facilitated. The specific information that the headrest needs to be shifted can be obtained according to the target shifting information of the headrest through the deviation between the actual position information and the historical position information of the passenger. Noise reduction processing is carried out while the headrest posture adjusting structure is adjusted, noise reduction is carried out all the time when the head of a passenger rotates, and the noise reduction effect is improved.

Description

Technical Field

[0001] This application relates to the field of headrest technology, and in particular to a noise reduction method for an automotive headrest and an automotive headrest. Background Technology

[0002] Conventional active noise cancellation technologies typically focus on controlling overall cabin noise, integrating simple speakers or sensors into the headrest, resulting in limited functionality. The head area is susceptible to multi-directional noise from wind and tires, and when users look in the side mirrors, the accompanying noise can amplify the noise during audio and video playback, leading to poor noise cancellation effectiveness.

[0003] Therefore, how to reduce noise to improve the noise reduction effect is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0004] The purpose of this application is to provide a noise reduction method for a car headrest and a car headrest, in order to solve the problems of poor noise reduction effect caused by single noise reduction and loud noise.

[0005] To solve the above-mentioned technical problems, this application provides a noise reduction method for a car headrest, which is applied to a car headrest. The car headrest includes a head posture detection module, a control module and a headrest posture adjustment mechanism, and both the headrest side wings and the headrest body are provided with noise reduction modules.

[0006] The control headrest posture detection module collects the passenger's head image corresponding to the car headrest, and analyzes and processes it to obtain the spatial position information and posture angle information of the passenger's head relative to the headrest side wings and the headrest body;

[0007] The headrest target offset information is determined based on spatial location information and attitude angle information; wherein, the headrest target offset information is obtained from the actual position information of the passenger on the headrest side wing and headrest body, the historical position information of the previous collection cycle, and / or the position information predicted by the passenger on the headrest side wing and headrest body corresponding to the preset collection cycle.

[0008] The headrest posture adjustment mechanism is controlled to adjust the current headrest posture information based on the headrest target offset information; and the noise reduction module is used to reduce the noise of the current headrest.

[0009] On the one hand, the headrest target offset information is determined based on spatial location information and attitude angle information, including:

[0010] Acquire the actual spatial location information and actual attitude angle information corresponding to the current acquisition cycle;

[0011] Obtain the first mapping relationship between the head coordinate system and the headrest coordinate system, where the spatial position information and posture angle information are located;

[0012] The corresponding actual position information is determined based on the actual spatial position information, the actual attitude angle information, and the first mapping relationship;

[0013] Obtain the historical spatial location information and historical attitude angle information corresponding to the previous acquisition cycle of the current acquisition cycle;

[0014] The corresponding historical location information is determined based on historical spatial location information, historical attitude angle information, and the first mapping relationship;

[0015] The headrest target offset information is determined based on the actual location information and the historical location information.

[0016] On the other hand, the corresponding actual position information is determined based on the actual spatial position information, the actual attitude angle information, and the first mapping relationship, including:

[0017] With the geometric center point of the headrest body as the origin, a headrest coordinate system is established along the horizontal, longitudinal and vertical directions of the vehicle, and the boundary coordinates of the headrest body and the opening and closing boundary coordinates of the headrest side wings are marked to form the spatial range of the vehicle headrest.

[0018] A head coordinate system is established with the geometric center of the passenger's head as the origin, along the left-right direction, the front-back direction, and the vertical direction of the passenger's head.

[0019] The first coordinate information of the head coordinate system, which contains the actual spatial location information and the actual posture angle information, is transformed to the headrest coordinate system to obtain the second coordinate information;

[0020] The first relative position information between the passenger's head and the headrest body is determined based on the origin information and spatial area range corresponding to the second coordinate information.

[0021] The second relative position information between the passenger's ear and the headrest side wings is determined based on the second coordinate information of the headrest coordinate system where the actual posture angle information is located;

[0022] The actual location information is determined based on the first relative location information and the second relative location information.

[0023] On the other hand, headrest target offset information is determined based on spatial location information and attitude angle information, including:

[0024] Based on the current acquisition cycle, obtain the historical spatial location information and historical attitude angle information corresponding to the preset acquisition cycle;

[0025] Obtain the first mapping relationship between the head coordinate system and the headrest coordinate system for each historical spatial location information and each historical posture angle information;

[0026] The corresponding historical location information is determined based on each historical spatial location information, each historical attitude angle information, and the first mapping relationship;

[0027] Head movement trend information is obtained by performing trend fitting processing based on historical location information.

[0028] The head target position information is predicted based on head movement trend information;

[0029] The headrest target offset information is determined based on the head target position information and the current position information.

[0030] On the other hand, trend fitting processing based on historical location information yields head movement trend information, including:

[0031] The first change direction and the first change rate are determined based on the historical attitude angle information.

[0032] If the first direction of change is the same within multiple consecutive sampling periods, and the first rate of change is greater than a preset speed, then the trend direction corresponding to the head movement trend information is determined.

[0033] Based on historical location information, information fitting processing is performed to obtain motion information corresponding to head movement trend information;

[0034] The head movement trend information is determined based on the trend direction and the movement information.

[0035] On the other hand, after obtaining head movement trend information by trend fitting based on historical location information, the process also includes:

[0036] A behavioral habit rule base corresponding to passengers is obtained in advance, wherein the behavioral habit rule base is extracted by clustering various behavioral habits;

[0037] The first correction parameter is obtained by matching the habit rule base with the passenger's historical behavior habits.

[0038] The head movement trend information is corrected according to the first correction parameter to obtain new head movement trend information, so as to proceed to the step of predicting the head target position information based on the head movement trend information.

[0039] On the other hand, after obtaining head movement trend information by trend fitting based on historical location information, the process also includes:

[0040] A micro-expression motion rule base corresponding to the passenger is obtained in advance, wherein the micro-expression motion rule base is obtained through the mapping relationship between each eye micro-expression, spatial position information and posture angle information;

[0041] The second correction parameter is obtained by matching the micro-expression movement rule library with the passenger's historical eye micro-expressions;

[0042] The head movement trend information is corrected according to the second correction parameter to obtain new head movement trend information, so as to proceed to the step of predicting the head target position information based on the head movement trend information.

[0043] On the other hand, after obtaining head movement trend information by trend fitting based on historical location information, the process also includes:

[0044] A road condition motion rule base for passengers under road condition events is obtained in advance, wherein the road condition motion rule base is obtained by extracting the motion information of passengers' heads under each road condition event;

[0045] Pre-set the car navigation system to execute warnings for various historical road condition events ahead;

[0046] The third correction parameter is obtained by matching the road condition movement rule base with historical road condition events;

[0047] The head movement trend is corrected based on the third correction parameter and the warning execution operation information to obtain new head movement trend information, so as to proceed to the step of predicting the head target position information based on the head movement trend information.

[0048] On the other hand, the noise reduction module is used to reduce the noise in the current headrest environment, including:

[0049] The relative positional deviation between the noise reduction module of the current headrest and the passenger's ear is determined based on the headrest target offset information; wherein, the relative positional deviation includes distance positional deviation, angle positional deviation and comprehensive positional deviation;

[0050] The distance position deviation, the angle position deviation, and the comprehensive position deviation are compared with their respective thresholds to determine the corresponding noise reduction strategies.

[0051] The noise at the current headrest is processed according to each noise reduction strategy;

[0052] Correspondingly, the process of determining the noise reduction strategy includes:

[0053] If the distance position deviation is greater than 0, the acoustic gain is increased to compensate for the energy attenuation during the propagation of the acoustic wave; if the distance position deviation is less than 0, the acoustic gain is reduced, and the howling frequency is filtered by notch filtering according to the howling suppression strategy.

[0054] If the angular position deviation is not equal to 0, the phase modulation of the noise reduction module is adjusted to correct the main lobe direction of the sound wave beam to the direction of the ear canal, and multiple microphones on the side of the headrest are used to collect the noise around the ear to obtain the noise spectrum, thereby achieving noise reduction processing.

[0055] If the overall position deviation is greater than 1, the mapping relationship between historical offset and noise reduction parameters is invoked, the target parameter is matched according to the mapping relationship, and noise reduction processing is performed according to the target parameter.

[0056] To solve the above-mentioned technical problems, this application also provides an automotive headrest, including a head posture detection module, a control module and a headrest posture adjustment mechanism, and both the headrest side wings and the headrest body are provided with noise reduction modules;

[0057] The headrest posture detection module, the control module, and the headrest posture adjustment mechanism are connected in sequence; the noise reduction module is connected to the control module.

[0058] The headrest posture detection module is used to collect the passenger's head image corresponding to the car headrest, and analyze and process it to obtain the spatial position information and posture angle information of the passenger's head relative to the headrest side wings and the headrest body.

[0059] The control module is used to execute the steps of the noise reduction method for the car headrest described above, so as to achieve noise reduction processing.

[0060] This application provides a noise reduction method for a car headrest. First, the car headrest includes a head posture detection module for real-time monitoring of the passenger's posture and spatial position information. A headrest posture adjustment mechanism is used to subsequently control the adjustment of the headrest body and side wings, shifting them towards the direction the passenger's head is tilting to shorten the distance deviation between the noise reduction module and the passenger's ears. Noise reduction modules are installed on both the headrest body and side wings, compared to conventional solutions where only the headrest body has a noise reduction module. This expands the coverage area of ​​the noise reduction modules and increases the noise reduction range, improving the noise reduction effect. Second, the headrest posture detection module acquires the passenger's head image corresponding to the car headrest, and analyzes and processes it to obtain the spatial position information and posture angle information of the passenger's head relative to the headrest side wings and headrest body. Using the head image to represent the passenger's contour features requires relatively little computation and has low hardware requirements; basic position determination can be achieved using a 2D camera, obtaining three-dimensional spatial position information and posture angle information of the head relative to the headrest side wings and headrest body. Then, the headrest target offset information is determined based on spatial location information and posture angle information. Here, the position information of the passenger on the headrest side wing and headrest body is determined by spatial location information and posture angle information, so that the noise reduction module and the passenger's ear maintain a stable relative position, which is conducive to subsequent adjustment of the headrest posture adjustment mechanism. The headrest target offset information can be obtained by the deviation between the passenger's actual position information and historical position information, which is convenient for real-time noise reduction. Alternatively, it can be predicted by the position information corresponding to the preset collection period of the passenger on the headrest side wing and headrest body, which is convenient for predictive active noise reduction. This application can realize predictive noise reduction during the setting of follow-up noise reduction, improving the diversity and flexibility of noise reduction. Finally, the headrest posture adjustment mechanism is controlled to adjust the current headrest posture information according to the headrest target offset information; and the noise reduction module is used to reduce the noise of the current headrest. By adjusting the headrest posture adjustment structure while performing noise reduction, noise reduction is achieved at all times during the passenger's head rotation, improving the noise reduction effect.

[0061] In addition, this application also provides a car headrest that has the same beneficial effects as the noise reduction method of the car headrest described above. Attached Figure Description

[0062] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0063] Figure 1 A flowchart illustrating a noise reduction method for an automotive headrest provided in this application embodiment;

[0064] Figure 2 A schematic diagram of the external shape of a car headrest provided in an embodiment of this application;

[0065] Figure 3 This is a schematic diagram of the structure of a car headrest provided in an embodiment of this application;

[0066] Figure 4 A flowchart illustrating another noise reduction method for a car headrest provided in this application embodiment;

[0067] Figure 5 A structural diagram of a noise reduction device for an automotive headrest provided in an embodiment of this application;

[0068] Figure 6 This is a structural diagram of another noise reduction device for a car headrest provided in an embodiment of this application. Detailed Implementation

[0069] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of this application.

[0070] The core of this application is to provide a noise reduction method for a car headrest and a car headrest, in order to solve the problems of poor noise reduction effect caused by single noise reduction and loud noise.

[0071] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0072] With the rapid development of the automotive industry and the increasing demands of consumers for in-vehicle comfort, noise control technology has become an important research direction in modern automotive design. In-vehicle noise mainly originates from the external environment (such as wind noise and tire noise) and in-vehicle equipment (such as the engine and air conditioning). Traditional sound insulation materials and passive noise reduction technologies are no longer sufficient to meet increasingly stringent comfort requirements. Active noise cancellation (ANC) technology detects noise and emits sound waves of opposite phase to cancel it out, becoming an important means of solving in-vehicle noise problems. However, the application of active noise cancellation technology in the headrest area is still in its early stages. Conventional methods integrate simple noise reduction devices into the headrest itself, offering limited functionality. Noise still exists when the user turns their head, and conventional noise reduction devices result in significant noise distortion during audio and video playback, leading to poor noise reduction effects and a poor user experience. Therefore, the noise reduction method for automotive headrests provided in this application can solve the aforementioned technical problems.

[0073] Figure 1 A flowchart illustrating a noise reduction method for an automotive headrest provided in this application embodiment is shown below. Figure 1 As shown, this is applied to automotive headrests. The automotive headrest includes a head posture detection module, a control module, and a headrest posture adjustment mechanism. Both the headrest side wings and the headrest body are equipped with noise reduction modules.

[0074] S11: Control the headrest posture detection module to collect the passenger's head image corresponding to the car headrest, and analyze and process it to obtain the spatial position information and posture angle information of the passenger's head relative to the headrest side wings and the headrest body;

[0075] S12: Determine the headrest target offset information based on spatial location information and attitude angle information;

[0076] Among them, the headrest target offset information is obtained from the actual position information of the passenger on the headrest side wing and the headrest body, the historical position information of the previous collection cycle, and / or the position information of the passenger on the headrest side wing and the headrest body corresponding to the preset collection cycle.

[0077] S13: Control the headrest posture adjustment mechanism to adjust the current headrest posture information according to the headrest target offset information; and use the noise reduction module to reduce the noise of the current headrest.

[0078] Specifically, Figure 2 This is a schematic diagram of the shape of a car headrest provided in an embodiment of this application, as shown below. Figure 2As shown, the headrest includes headrest side wings 2 and headrest body 1. The headrest body is the core support area, and the headrest side wings 2 are the two sides of the headrest body 1, resembling a structure with wings. In conventional solutions, only the headrest body 1 has a noise reduction module 3. In this application, both the headrest body 1 and the headrest side wings 2 are equipped with noise reduction modules 3. Regarding the type of noise reduction module 3, it can be a sound-absorbing filling material filled inside the headrest body and headrest side wings, or it can be a sound-insulating lining that blocks some noise penetration and transmission between the filling material and the headrest fabric. It can also be an active noise reduction module with a built-in miniature microphone and speaker, which actively cancels noise in a specific frequency band by emitting sound waves with the opposite phase to the noise. It can also be superimposed, etc., without limitation. This application takes into account the two types of active noise reduction, namely follow-up noise reduction and predictive noise reduction, and can add other noise reduction types on the basis of active noise reduction.

[0079] Figure 3 This is a schematic diagram of the structure of a car headrest provided in an embodiment of this application, as shown below. Figure 3 As shown, the system includes a head posture detection module, a control module, and a headrest posture adjustment mechanism. The head posture detection module is implemented using a passenger monitoring system and includes a camera unit, an image processing unit, and a posture analysis unit. The camera unit captures the passenger's head image corresponding to the headrest. Analysis and processing yield the spatial position and posture angle information of the passenger's head relative to the headrest's sides and body. This requires recognizing head contour features from the passenger's head image, and then using these features, the posture analysis unit obtains the spatial position and posture angle information of the passenger's head relative to the headrest's sides and body.

[0080] The spatial position information of the passenger's head relative to the headrest wing and the headrest body is a three-dimensional spatial position calculated using the headrest wing and the headrest body. Attitude angle information includes pitch angle, yaw angle, and roll angle.

[0081] The system extracts head contour features from the head image using algorithms such as edge detection and threshold segmentation to identify key head contour points, including the highest point of the head, the left and right temples (temples), the jaw angle, and the chin tip. These 2D coordinates are quickly identified and labeled. An internal, standardized 3D geometric model of the head (such as an ellipsoidal model) is used to match and align the extracted 2D contour feature points with these model's features. Based on the matched feature point coordinates and the geometric model, the system calculates the head's 3D spatial position and pose angle information.

[0082] In step S12, the headrest target offset information is determined based on the spatial position and attitude angle information. This headrest target offset information corresponds to the offset of the target point that the headrest attitude adjustment mechanism needs to reach. It can be obtained through real-time calculation or prediction. The headrest target offset information is obtained from the actual position information of the passenger on the headrest side wing and headrest body, the historical position information of the previous collection cycle, and / or the predicted position information corresponding to the preset collection cycle of the passenger on the headrest side wing and headrest body.

[0083] In the real-time calculation and following mode, the actual position information in the headrest coordinate system is determined based on the actual spatial position information and actual attitude angle information of the current acquisition cycle. The historical position information in the headrest coordinate system is determined based on the historical spatial position information and historical attitude angle information of the previous acquisition cycle. The target offset information is then determined using the actual position information and the historical position information.

[0084] If the method is predictive, multiple historical position information based on the headrest coordinate system will be determined based on multiple historical spatial position information and multiple historical posture angle information. Then, head movement trend information will be obtained through trend fitting. The head target position information will be predicted based on the head movement trend information. The head target offset information will be determined based on the head target position information and the current position information.

[0085] Regarding the two methods mentioned above, noise reduction processing can be adopted in combination with / or to enhance the versatility and flexibility of noise reduction.

[0086] In step S13, the headrest posture adjustment mechanism is controlled to adjust the current headrest posture information based on the headrest target offset information, and the subsequent noise reduction module performs noise reduction processing. The two can be performed simultaneously without any order.

[0087] The headrest posture adjustment mechanism includes a fore-and-aft position adjustment unit and an angle adjustment unit. Each unit can be implemented using a micro motor with a gear mechanism or a lead screw structure to drive the headrest body to move in the fore-and-aft direction and / or rotate around a support shaft, thereby changing the posture of the headrest body relative to the passenger's head. The controller sends drive commands to the headrest posture adjustment mechanism, causing the headrest to adjust to a position and angle that matches the passenger's head.

[0088] The noise reduction module includes a noise acquisition unit, a noise-canceling speaker, and a digital signal processor. The noise acquisition unit collects environmental noise signals generated during vehicle operation and sends these signals to the digital signal processor. The noise-canceling speaker is positioned on the headrest body and side wings near the passenger's ears to output reverse sound waves. The digital signal processor performs digital filtering and spectral analysis on the acquired noise signals, generates a reverse sound wave control signal to cancel out environmental noise, and controls the noise-canceling speaker to output the reverse sound waves.

[0089] Regarding noise reduction, it can be either follow-up noise reduction or predictive noise reduction. Regardless of the noise reduction method, it is implemented by following the steps described above.

[0090] Figure 4 A flowchart of another noise reduction method for a car headrest provided in this application embodiment is shown below. Figure 4 As shown, it includes:

[0091] S21: Obtain head pose information;

[0092] S22: Determine if the head posture information has changed; if so, proceed to step S23.

[0093] S23: Calculate headrest target offset information;

[0094] S24: Drive the headrest posture adjustment mechanism to adjust according to the headrest target offset information;

[0095] S25: Obtain the current posture information of the adjusted headrest;

[0096] S26: Update noise reduction parameters;

[0097] S27: Output reverse sound waves to achieve noise reduction processing, and return to step S21.

[0098] This application provides a noise reduction method for a car headrest. First, the car headrest includes a head posture detection module for real-time monitoring of the posture and spatial position information of the passenger corresponding to the headrest. A headrest posture adjustment mechanism is used to subsequently control the adjustment of the headrest body and side wings, shifting them towards the direction the passenger's head is inclined, thereby reducing the distance deviation between the noise reduction module and the passenger's ear. Noise reduction modules are installed on both the headrest body and side wings, compared to conventional solutions where only the headrest body has a noise reduction module. This expands the coverage area of ​​the noise reduction modules and increases the noise reduction range, improving the noise reduction effect. Second, the headrest posture detection module is controlled to acquire the passenger's head image corresponding to the car headrest, and the analysis and processing are performed to obtain the spatial position information and posture angle information of the passenger's head relative to the headrest side wings and headrest body. Using the head image to represent the passenger's contour features requires relatively little computation and has low hardware requirements; basic position determination can be achieved using a 2D camera, obtaining three-dimensional spatial position information and posture angle information of the head relative to the headrest side wings and headrest body. Then, the headrest target offset information is determined based on spatial location information and posture angle information. Here, the position information of the passenger on the headrest side wing and headrest body is determined by spatial location information and posture angle information, so that the noise reduction module and the passenger's ear maintain a stable relative position, which is conducive to subsequent adjustment of the headrest posture adjustment mechanism. The headrest target offset information can be obtained by the deviation between the passenger's actual position information and historical position information, which is convenient for real-time noise reduction. Alternatively, it can be predicted by the position information corresponding to the preset collection period of the passenger on the headrest side wing and headrest body, which is convenient for predictive active noise reduction. This application can realize predictive noise reduction during the setting of follow-up noise reduction, improving the diversity and flexibility of noise reduction. Finally, the headrest posture adjustment mechanism is controlled to adjust the current headrest posture information according to the headrest target offset information; and the noise reduction module is used to reduce the noise of the current headrest. By adjusting the headrest posture adjustment structure while performing noise reduction, noise reduction is achieved at all times during the passenger's head rotation, improving the noise reduction effect.

[0099] In some embodiments, determining headrest target offset information based on spatial location information and attitude angle information includes:

[0100] Acquire the actual spatial location information and actual attitude angle information corresponding to the current acquisition cycle;

[0101] Obtain the first mapping relationship between the head coordinate system and the headrest coordinate system, where the spatial position information and posture angle information are located;

[0102] The corresponding actual position information is determined based on the actual spatial position information, the actual attitude angle information, and the first mapping relationship;

[0103] Obtain the historical spatial location information and historical attitude angle information corresponding to the previous acquisition cycle of the current acquisition cycle;

[0104] The corresponding historical location information is determined based on historical spatial location information, historical attitude angle information, and the first mapping relationship;

[0105] The headrest target offset information is determined based on the actual location information and historical location information.

[0106] Specifically, the spatial location information is obtained in the head coordinate system and the posture angle information is obtained in the headrest coordinate system. The two coordinate systems are mapped to determine the actual location information. Similarly, historical location information is obtained in the same way.

[0107] Regarding the first mapping relationship here, since the head coordinate system is dynamic, it is necessary to transform the coordinates of the head feature points to the fixed coordinate system of the headrest. The formula is as follows:

[0108] ; (1)

[0109] in, The coordinates of the head feature points in the head coordinate system represent the spatial location information. The attitude rotation matrix is ​​composed of attitude angle information. It is a translation vector. These are the final coordinates in the headrest coordinate system. The translation vector is the spatial difference between the origins of the headrest coordinate system and the head coordinate system.

[0110] This embodiment establishes a first mapping relationship between the head coordinate system and the headrest coordinate system. This mapping, combined with the actual spatial position and posture angle of the head, determines the relative position information to facilitate the determination of target offset information. This solves the problem of quantifying the spatial position between a dynamic head and a fixed headrest, providing a precise coordinate reference for headrest noise reduction and adaptive adjustment functions. It avoids the ambiguity of estimations based on experience and meets the high-precision requirements of intelligent automotive cockpit functions. A posture angle rotation matrix is ​​simultaneously introduced to compensate and correct the coordinates of head feature points, ensuring that even with changes in head posture, the true position of feature points relative to the headrest body / side wings can be accurately calculated. This provides a stable input basis for dynamic headrest adjustment and noise wave coupling.

[0111] In some embodiments, determining the corresponding actual position information based on actual spatial position information, actual attitude angle information, and a first mapping relationship includes:

[0112] With the geometric center point of the headrest body as the origin, a headrest coordinate system is established along the horizontal, longitudinal and vertical directions of the vehicle, and the boundary coordinates of the headrest body and the opening and closing boundary coordinates of the headrest side wings are marked to form the spatial range of the vehicle headrest.

[0113] A head coordinate system is established with the geometric center of the passenger's head as the origin, along the left-right direction, the front-back direction, and the vertical direction of the passenger's head.

[0114] The first coordinate information of the head coordinate system, which contains the actual spatial location information and the actual posture angle information, is transformed to the headrest coordinate system to obtain the second coordinate information;

[0115] The first relative position information between the passenger's head and the headrest body is determined based on the origin information and spatial area range corresponding to the second coordinate information.

[0116] The second relative position information between the passenger's ear and the headrest side wings is determined based on the second coordinate information of the headrest coordinate system where the actual posture angle information is located;

[0117] The actual location information is determined based on the first relative location information and the second relative location information.

[0118] Specifically, a head coordinate system is established with the geometric center of the passenger's head as the origin, along the left-right, front-back, and vertical directions of the head. When establishing a fixed coordinate system like the headrest coordinate system, the headrest coordinate system is established with the geometric center of the headrest body as the origin, along the horizontal, longitudinal, and vertical directions of the vehicle. At this time, it is necessary to record the boundary coordinates of the headrest body and the opening and closing coordinates of the headrest side wings to form the spatial range of the headrest component.

[0119] The process for determining the second coordinate system information can be obtained from formula (1) in the above embodiment, and will not be elaborated here. Regarding the first relative position information between the head and the headrest body, it is based on the pre-calibrated spatial range. The head origin Op coordinate corresponding to the converted second coordinate information is substituted into it. If the coordinate information of the second coordinate information is within the three-axis range of the headrest body, it can be determined that the passenger's head is located within the headrest body area. If the X-axis coordinate of the second coordinate information exceeds the range of the headrest body but falls within the X-axis range of the headrest side wing, it indicates that the head is biased towards the headrest side wing area. If the Y-axis coordinate of the second coordinate information is too small, it indicates that the head is close to and fits against the headrest. If it is too large, it indicates that the head is far away.

[0120] By pre-calibrating the spatial range of the headrest side wings, and using the second coordinate information of the headrest coordinate system based on the actual posture angle information, the coordinate information of the passenger's left and right tragus points (second coordinate information) can be calculated. If the left tragus point corresponding to the second coordinate information falls within the range of the left side wing of the headrest, it means that the left ear is within the effective coverage area of ​​the left side wing. If the Y-axis coordinate of the right tragus point corresponding to the second coordinate information is within the optimal effective range of the headrest side wing, it means that the passenger's ear and the noise reduction components of the side wing are in the best coupling position. If the tragus point is outside the range of the side wing, the opening angle of the side wing or the position of the headrest needs to be adjusted so that the ear falls into the effective area.

[0121] The actual location information is obtained by combining the first relative position and the second relative position.

[0122] The spatial coordinate transformation process based on the headrest-head dual coordinate system provided in this embodiment enables accurate determination of the relative position of the passenger's head with respect to the headrest body and the headrest side wings, thereby ensuring the accuracy of the actual position information and facilitating the subsequent determination of head target offset information.

[0123] In some embodiments, determining headrest target offset information based on spatial location information and attitude angle information includes:

[0124] Based on the current acquisition cycle, obtain the historical spatial location information and historical attitude angle information corresponding to the preset acquisition cycle;

[0125] Obtain the first mapping relationship between the head coordinate system and the headrest coordinate system for each historical spatial location information and each historical posture angle information;

[0126] The corresponding historical location information is determined based on each historical spatial location information, each historical attitude angle information, and the first mapping relationship;

[0127] Head movement trend information is obtained by performing trend fitting processing based on historical location information.

[0128] The head target position information is predicted based on head movement trend information;

[0129] The headrest target offset information is determined based on the head target position information and the current position information.

[0130] Specifically, the process for determining historical location information is the same as in the above embodiments, and will not be repeated here. Please refer to the above embodiments. Based on the historical location information, trend fitting is performed. Here, trend fitting can be linear trend fitting. If the passenger's head movement is gentle, linear regression is performed on the three axes of the headrest coordinate system to obtain the rate of change of the coordinates over time. The rate of change directly reflects the direction and speed of the passenger's head movement.

[0131] If the passenger's head movements are complex, such as turning or lowering their head, a quadratic polynomial can be used to fit the trajectory, or Kalman filtering can be used to eliminate noise and accurately extract the movement trend. Simultaneously, by combining historical patterns of attitude angle changes, the future values ​​of the attitude angles can be predicted to obtain head movement trend information. This head movement trend information is accurate to a specific future time, thus determining the head target position information at that specific future time. Based on the head target position information and the current position information, the headrest target offset information is determined.

[0132] The headrest target offset information prediction method provided in this embodiment collects and stores the temporal position and posture data of the passenger's head in the headrest coordinate system, extracts the head movement pattern through trend fitting, predicts the future head target position, and then generates the headrest migration distance, direction and angle parameters to avoid the headrest adjustment lagging behind the head movement. Based on the historical posture pattern, the migration angle is corrected to ensure that the noise reduction module is always aligned with the ear; the trend fitting avoids frequent start and stop of the headrest, improving passenger comfort.

[0133] In some embodiments, head movement trend information is obtained by trend fitting based on historical location information, including:

[0134] The first change direction and the first change rate are determined based on the historical attitude angle information.

[0135] If the first direction of change is the same in multiple consecutive sampling periods, and the first rate of change is greater than the preset speed, the trend direction corresponding to the head movement trend information is determined.

[0136] Based on historical location information, information fitting processing is performed to obtain motion information corresponding to head movement trend information;

[0137] Determine head movement trend information based on trend direction and movement information.

[0138] Specifically, in the process of determining the head movement trend information, the corresponding first change direction and first change rate are determined based on the historical posture angle information. If the first change direction is the same in multiple consecutive sampling periods, it indicates that there is a trend towards that change direction. To be on the safe side, the trend direction corresponding to the head movement trend information is further clarified by comparing the first change rate with the preset speed.

[0139] Information fitting based on historical location information is the motion information corresponding to the head movement trend information determined after eliminating position information deviations caused by interference signals. That is, the motion information is the step length information of the movement.

[0140] The head movement trend information is obtained by merging the trend direction and movement information.

[0141] Furthermore, the head posture detection module continuously collects passenger head posture angle information and sends it to the control module. The head posture angle information includes: left and right rotation angles and forward and backward pitch angles; and the rate of change of head posture. The control module caches the head posture angle information within a preset time window, forming a historical head posture data sequence for subsequent trajectory prediction calculations.

[0142] The control module analyzes the head rotation trend based on the current head posture angle information and historical data sequences. Specifically, this includes: calculating the direction of change of the head posture angle information; calculating the rate of change of the head posture; and determining whether the head rotation meets preset continuous rotation conditions. When it detects that the head posture angle information changes in the same direction over multiple consecutive sampling periods, and the rate of change is greater than a preset threshold, the control module determines that the head will continue to rotate in the current direction and predicts the target head posture within a preset prediction time based on the rate of change. The prediction time window is shorter than the response time of the headrest posture adjustment mechanism and the active noise cancellation system. Based on the predicted target head posture, the corresponding target headrest offset direction and offset amount are calculated. Before the head reaches the target posture, a drive command is sent to the headrest posture adjustment mechanism, driving the headrest body to offset in the predicted direction in advance.

[0143] This embodiment provides head movement trend information obtained by trend fitting based on historical position information. By combining historical position information, historical posture angle information, change direction and change rate, the headrest is in a position that matches the head posture when the head completes the rotation, thereby shortening the actual follow-up response time.

[0144] In some embodiments, after obtaining head movement trend information by trend fitting based on historical location information, the method further includes:

[0145] A behavioral habit rule base corresponding to passengers is obtained in advance, wherein the behavioral habit rule base is extracted by clustering various behavioral habits;

[0146] The first correction parameter is obtained by matching the passenger's historical behavior with a habit rule base.

[0147] The head motion trend information is corrected based on the first correction parameter to obtain new head motion trend information, so as to proceed to the step of predicting the head target position information based on the head motion trend information.

[0148] Specifically, a time-series database of behavioral habit tags is established. Each record includes a timestamp, location, posture, and driver behavior. A clustering algorithm is used to form a behavioral habit rule base based on the correlation between typical driver behaviors and passenger head positions. For example, when the driver activates the right turn signal and the vehicle speed is <30km / h, in 85% of scenarios, the front passenger's head will turn 5°~15° to the right, with the ear close to the right side. When the driver brakes and decelerates and the vehicle speed is >60km / h, in 78% of scenarios, the passenger's head will tilt forward 10°~20°, away from the headrest. When the driver is cruising straight at high speed, the passenger's head position is stable, with a posture angle fluctuation of <3°.

[0149] When matching passengers' historical behavioral habits to the habit rule base, the first correction parameter is obtained, and its formula is as follows:

[0150] ; (2)

[0151] in, , , , The parameters for head movement trend information are, in order: the first parameter, the second parameter, the third parameter, and the fourth parameter. It is the angle of opening and closing outwards; , , , The fifth, sixth, seventh, and eighth parameters, respectively, represent the passenger's historical behavioral habits in the head coordinate system. , , , The weights are, in order, the first weight coefficient, the second weight coefficient, the third weight coefficient, and the fourth weight parameter of the first correction parameter. The first correction parameter is determined by the probability of the behavior occurring. If the rule matching degree is 85%, then the weight coefficient is 0.85.

[0152] The above formula (2) can be used to obtain new head movement trend information, specifically a four-dimensional parameter set.

[0153] This embodiment constructs a database of historical passenger head positions with behavioral labels, mines the correlation rules between driver behavior and passenger head posture, first fits motion trends based on historical positions to obtain basic transfer parameters, and then combines behavioral rules to complete parameter weighting and correction. It identifies driver behavior in advance, predicts passenger head movement trends, and adjusts the headrest earlier than pure position prediction. Combined with individual driving habits, it avoids frequent and ineffective headrest adjustments, improving noise reduction and ride comfort.

[0154] In some embodiments, after obtaining head movement trend information by trend fitting based on historical location information, the method further includes:

[0155] The micro-expression motion rule base corresponding to the passenger is obtained in advance. The micro-expression motion rule base is obtained through the mapping relationship between each eye micro-expression, spatial position information and posture angle information.

[0156] The second correction parameter is obtained by matching the passenger's historical eye micro-expressions with a micro-expression motion rule library.

[0157] The head motion trend information is corrected according to the second correction parameter to obtain new head motion trend information, so as to proceed to the step of predicting the head target position information based on the head motion trend information.

[0158] Specifically, the driver monitoring system collects micro-expression features of the eyes, including eye gaze direction (e.g., left-eye, right-eye, forward-looking, downward-looking), blink frequency, and pupil dilation amplitude. These micro-expressions are then encoded. A time-series database is built, storing associated data according to timestamps. Machine learning algorithms are used to uncover the inherent patterns between passenger eye micro-expressions and their head position and posture information, forming a micro-expression movement rule base. For example, micro-expression F1 (left-eye looking + pupil dilation) indicates that within 500ms, in 82% of scenarios, the passenger's head will turn 8° to the left, the left ear will move closer to the left wing, and the head's Y-axis coordinate will shift forward by 38mm; micro-expression F2 (right-eye looking + pupil constriction) indicates that within 500ms, in 79% of scenarios, the passenger's head will turn 10° to the right, the right ear will move closer to the right wing; and micro-expression F3 (downward-looking + high-frequency blinking) indicates that within 500ms, in 75% of scenarios, the passenger's head will tilt downwards by 12°, moving away from the headrest.

[0159] The second correction parameter is obtained by matching the passenger's historical eye micro-expressions with a micro-expression movement rule library, as shown in the following formula:

[0160] ; (3)

[0161] in, , , , The first, second, third, and fourth parameters of the head movement trend information are listed in order. , , , These are the ninth, tenth, eleventh, and twelfth parameters of micro-expressions in the head coordinate system; , , , The weights are, in order, the fifth, sixth, seventh, and eighth weights of the second correction parameter.

[0162] For example, the basic prediction is that the left wing needs to open inward by 2° and the headrest Y-axis needs to move forward by 3mm; through micro-expression matching, the passenger exhibits F1 (left gaze + pupil dilation), matching the above micro-expression motion rule library, the left wing needs to open outward by an additional 5° and the headrest Y-axis needs to move forward by an additional 5mm, with a weight k=0.82; the final transfer parameters are... The value is -2 + 0.82 × 5 = 2.1, and the opening angle is 2.1°. The value is 3 + 0.82 × 5 = 7.1 mm, which means it should be moved forward by 7.1 mm.

[0163] The above formula (3) can be used to obtain new head movement trend information, specifically a four-dimensional parameter set.

[0164] This embodiment provides a database of historical passenger head positions with micro-expression tags for eyeballs. It mines the association rules between driver's micro-expressions and changes in passenger head posture. First, it obtains basic migration parameters by fitting motion trends based on historical positions. Then, it combines micro-expression intentions to complete parameter weighting correction. This triggers headrest adjustment earlier than pure position prediction, completes position adaptation before the passenger's head begins to move, and converts the passenger's operation intentions into headrest adjustment commands through micro-expressions, resulting in more accurate adaptation.

[0165] In some embodiments, after obtaining head movement trend information by trend fitting based on historical location information, the method further includes:

[0166] The road condition motion rule base for passengers under various road condition events is obtained in advance. The road condition motion rule base is obtained by extracting the head motion information of passengers under various road condition events.

[0167] Pre-set the car navigation system to execute warnings for various historical road condition events ahead;

[0168] The third correction parameter is obtained by matching the road condition movement rule base with historical road condition events;

[0169] Based on the third correction parameter and the early warning execution information, the head movement trend is corrected to obtain new head movement trend information, so as to proceed to the step of predicting the head target position information based on the head movement trend information.

[0170] Specifically, the road condition motion rules are associated with the road condition characteristics of the in-vehicle navigation route. They are extracted based on the passenger's head movement patterns, such as left / right turns, highway ramps, speed bumps, and sharp turns, through road condition events along the navigation route. Specifically, machine learning algorithms (such as decision trees and association rule mining) are used to refine the passenger's head movement patterns under different road condition events, forming a road condition motion rule library for each event. For example, when navigation triggers "turn left 500m ahead," within 400ms, in 88% of scenarios, the passenger's head will turn 8° to the left, with the left ear closer to the left wing, and the head's Y-axis (forward / backward) movement will be 36mm forward. When navigation triggers "enter a highway curve 300m ahead (curvature > 15°)," within 500ms, in 92% of scenarios, the passenger's head will turn 10° towards the inside of the curve, requiring a slight adjustment of the headrest towards the inside wing. When the navigation triggers "passing a speed bump 200m ahead", within 300ms, in 75% of the scenarios, the passenger's head tilts upward by 5°, moving away from the headrest body, and the headrest needs to move upward by 24mm.

[0171] The pre-set car navigation system executes warnings for various historical road condition events ahead. The navigation system pushes road condition events ahead in real time. Here, a trigger threshold is set. For example, when the distance to the road condition event is 500-800m, if the right turn is expected 800m ahead, the system initiates a pre-judgment preparation for headrest adjustment; when the distance to the road condition event is 200-300m, the system officially outputs the headrest relocation command, reserving adjustment response time. The initiation and execution operation here can be an initiation of the pre-judgment preparation operation and an output of the headrest relocation command, etc.

[0172] The third correction parameter is obtained by matching historical road condition events with a road condition motion rule base, as shown in the following formula:

[0173] ; (4)

[0174] in, , , , The first, second, third, and fourth parameters of the head movement trend information are listed in order. , , , These are the thirteenth, fourteenth, fifteenth, and sixteenth parameters corresponding to the road condition event in the head coordinate system; , , , The weighted parameters are, in order, the ninth, tenth, eleventh, and twelfth weighted parameters of the third correction parameter. These weighted parameters are determined by the correlation between road condition events and passenger movement.

[0175] It should be noted that the passenger's personal behavioral habits, micro-expressions, and traffic events corresponding to the navigation system in the above embodiments can be combined according to the actual situation, and no limitation is made here.

[0176] This embodiment constructs a database of historical passenger head positions tagged with navigation traffic conditions, mines correlation rules between traffic events and changes in passenger head posture, first fits motion trends based on historical positions to obtain basic migration parameters, and then combines navigation traffic rules to complete parameter weighting correction. Headrest adjustment is completed before traffic events occur to avoid adjustment lag, and corrections are made for different traffic conditions to improve noise reduction and ride comfort. Combining navigation and vehicle data avoids the risk of misjudgment from a single sensor.

[0177] In some embodiments, the noise reduction module is used to reduce the noise level of the current headrest, including:

[0178] The relative positional deviation between the noise reduction module of the headrest and the passenger's ear is determined based on the headrest target offset information; the relative positional deviation includes distance positional deviation, angle positional deviation and comprehensive positional deviation.

[0179] The distance position deviation, angle position deviation and comprehensive position deviation are compared with their respective thresholds to determine the corresponding noise reduction strategies.

[0180] The noise reduction process is performed on the current headrest according to each noise reduction strategy.

[0181] Correspondingly, the process of determining the noise reduction strategy includes:

[0182] If the distance position deviation is greater than 0, the acoustic wave gain is increased to compensate for the energy attenuation during the propagation of the acoustic wave; if the distance position deviation is less than 0, the acoustic wave gain is reduced, and the howling frequency is filtered by notch filtering according to the howling suppression strategy.

[0183] If the angular position deviation is not equal to 0, the phase modulation of the noise reduction module is adjusted to correct the direction of the main lobe of the sound wave beam to the direction of the ear canal, and multiple microphones on the side of the headrest are used to collect the noise around the ear to obtain the noise spectrum, thereby achieving noise reduction processing.

[0184] If the overall position deviation is greater than 1, the mapping relationship between historical offset and noise reduction parameters is invoked, the target parameters are matched according to the mapping relationship, and noise reduction is performed according to the target parameters.

[0185] Specifically, regarding noise reduction processing, it mainly involves adjusting active noise reduction parameters. The relative positional deviation between the noise reduction module and the passenger's ear is determined based on the headrest target offset information. Here, the distance positional deviation is the difference between the distance between the noise reduction module and the passenger's ear under the current positional information and the distance under the historical positional information from the previous data collection period. The angular positional deviation corresponds to the deviation between the direct angle of the speaker sound wave from the noise reduction module and the ear canal orientation angle. The comprehensive positional deviation is the offset coefficient obtained by taking the square root of the sum of the squares of the distance positional deviation and the angular positional deviation.

[0186] The noise reduction strategy is determined by comparing the distance position deviation, angle position deviation and comprehensive position deviation with their respective thresholds; the strategies are determined based on the threshold comparisons for each parameter.

[0187] If the distance deviation is greater than 0, the acoustic gain is increased to compensate for energy attenuation during sound wave propagation. Adjusting the acoustic gain linearly increases the speaker output power according to the offset, compensating for energy attenuation during sound wave propagation. The filter bandwidth is optimized to broaden the noise reduction frequency band and cover low-to-mid-frequency noise that attenuates due to increased distance. This avoids insufficient energy of the anti-phase sound waves due to excessive distance, thus improving the noise reduction effect.

[0188] If the distance deviation is less than 0, the acoustic gain is reduced, and the howling frequency is filtered by notch filtering according to the howling suppression strategy. The feedback signal collected by the microphone is monitored in real time. When a howling frequency is detected, the frequency band is automatically notched to eliminate howling interference at close range, while maintaining the cancellation effect of mid-to-high frequency noise.

[0189] If the angular position deviation is not equal to 0, the phase modulation of the noise reduction module is adjusted to correct the direction of the main lobe of the sound wave beam to the direction of the ear canal, and multiple microphones on the side of the headrest are used to collect the noise around the ear to obtain the noise spectrum, thereby achieving noise reduction processing; solving the problem of cancellation failure caused by sound wave refraction and improving the noise reduction effect.

[0190] If the overall positional deviation is greater than 1, the mapping relationship between historical offsets and noise reduction parameters is invoked. The target parameters are matched based on this mapping relationship, and noise reduction is then performed according to the target parameters. The system invokes the historical offset-noise reduction parameter mapping table to match the optimal combination of gain, bandwidth, and directional parameters. The headrest motor is prioritized to correct the offset (such as forward movement / deflection), achieving a dual closed loop of offset correction and noise reduction optimization to adapt to complex head movement scenarios.

[0191] This embodiment quantifies the distance and angular offset between the headrest noise-canceling components and the passenger's ear, and specifically adjusts the acoustic gain, filtering bandwidth, and directivity parameters of the active noise cancellation system. Simultaneously, it optimizes the passive noise-canceling structure on the headrest sides, achieving adaptive maintenance of noise cancellation performance even under offset scenarios. No manual intervention from the passenger is required; noise cancellation parameters are optimized in real-time based on headrest offset, adapting to positional changes caused by head movement. This solves the problem of acoustic coupling failure caused by offset, ensuring that noise reduction fluctuations are controlled within an effective range.

[0192] Furthermore, this application also provides an automotive headrest, including a head posture detection module, a control module, and a headrest posture adjustment mechanism, and both the headrest side wings and the headrest body are provided with noise reduction modules;

[0193] The headrest posture detection module, control module, and headrest posture adjustment mechanism are connected in sequence; the noise reduction module is connected to the control module.

[0194] The headrest posture detection module is used to collect the passenger's head image corresponding to the car headrest, and analyze and process it to obtain the spatial position information and posture angle information of the passenger's head relative to the headrest side wings and the headrest body;

[0195] The control module is used to execute the steps of the above-mentioned noise reduction method for car headrests to achieve noise reduction processing.

[0196] Specifically, the controller is located in the vehicle seat control unit and connects to the headrest posture detection module, headrest posture adjustment mechanism, and noise reduction module via a communication interface. The headrest posture detection module detects the head position in real time, while the touch film and pressure sensor detect the head contact status, collaboratively adjusting the headrest position and noise reduction path. The noise reduction speaker and adjustment module simultaneously operate according to control commands, achieving precise noise reduction and dynamic support. The system as a whole switches between different operating modes based on the usage scenario; for example, it enters a low-power mode when the passenger is not in contact, and resumes full operation after contact.

[0197] For an introduction to the car headrest provided in this application, please refer to the above method embodiments. This application will not repeat the details here, but it has the same beneficial effects as the noise reduction method of the car headrest described above.

[0198] The above describes in detail the various embodiments of the noise reduction method for car headrests. Based on this, this application also discloses a noise reduction device for a car headrest corresponding to the above method, which is applied to a car headrest. The car headrest includes a head posture detection module, a control module, and a headrest posture adjustment mechanism, and both the headrest side wings and the headrest body are provided with noise reduction modules. Figure 5 This is a structural diagram of a noise reduction device for a car headrest provided in an embodiment of this application. Figure 5 As shown, the noise reduction device for the car headrest includes:

[0199] The analysis and processing module 11 is used to control the headrest posture detection module to collect the passenger's head image corresponding to the car headrest, and analyze and process it to obtain the spatial position information and posture angle information of the passenger's head relative to the headrest side wings and the headrest body.

[0200] The determination module 12 is used to determine the headrest target offset information based on spatial location information and attitude angle information; wherein, the headrest target offset information is obtained by the actual position information of the passenger on the headrest side wing and headrest body, the historical position information of the previous collection cycle, and / or the position information predicted by the passenger on the headrest side wing and headrest body corresponding to the preset collection cycle.

[0201] The adjustment module 13 is used to control the headrest posture adjustment mechanism to adjust the current headrest posture information according to the headrest target offset information; and to use the noise reduction module to reduce the noise of the current headrest.

[0202] Since the embodiments of the device part correspond to the embodiments described above, please refer to the embodiments described in the method part for the embodiments of the device part, and will not be repeated here.

[0203] For a description of the noise reduction device for a car headrest provided in this application, please refer to the above method embodiments. This application will not repeat the description here, as it has the same beneficial effects as the above-described noise reduction method for a car headrest.

[0204] Figure 6 A structural diagram of another noise reduction device for a car headrest provided in this application embodiment is shown below. Figure 6 As shown, the device includes:

[0205] Memory 21 is used to store computer programs;

[0206] Processor 22 is used to implement a noise reduction method for a car headrest when executing a computer program.

[0207] The processor 22 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 22 may be implemented using at least one of the following hardware forms: Digital Signal Processor (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 22 may also include a main processor and a coprocessor. The main processor, also known as the Central Processing Unit (CPU), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 22 may integrate a Graphics Processing Unit (GPU), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 22 may also include an Artificial Intelligence (AI) processor, which handles computational operations related to machine learning.

[0208] The memory 21 may include one or more computer-readable storage media, which may be non-transitory. The memory 21 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In this embodiment, the memory 21 is used to store at least the following computer program 211, which, after being loaded and executed by the processor 22, is capable of implementing the relevant steps of the noise reduction method for the car headrest disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 21 may also include an operating system 212 and data 213, etc., and the storage method may be temporary storage or permanent storage. The operating system 212 may include Windows, Unix, Linux, etc. The data 213 may include, but is not limited to, the data involved in the noise reduction method for the car headrest.

[0209] In some embodiments, the noise reduction device for the car headrest may further include a display screen 23, an input / output interface 24, a communication interface 25, a power supply 26, and a communication bus 27.

[0210] Those skilled in the field can understand, Figure 6 The structure shown does not constitute a limitation on the noise reduction device of the car headrest and may include more or fewer components than shown.

[0211] The processor 22 implements the noise reduction method for the car headrest provided in any of the above embodiments by calling instructions stored in the memory 21.

[0212] For a description of the noise reduction device for a car headrest provided in this application, please refer to the above method embodiments. This application will not repeat the description here, as it has the same beneficial effects as the above-described noise reduction method for a car headrest.

[0213] Furthermore, this application also provides a computer-readable storage medium storing a computer program, which, when executed by processor 22, implements the steps of the noise reduction method for the car headrest described above.

[0214] It is understood that if the methods in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and executes all or part of the steps of the methods in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0215] For a description of the computer-readable storage medium provided in this application, please refer to the above method embodiments. This application will not repeat the description here, but it has the same beneficial effects as the noise reduction method for the car headrest described above.

[0216] The above provides a detailed description of a noise reduction method for a car headrest and the car headrest itself. The various embodiments in the specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section. It should be noted that those skilled in the art can make several improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of this application.

[0217] It should also be noted that, in this specification, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

Claims

1. A noise reduction method for a car headrest, characterized in that, The invention is applied to automotive headrests, which include a head posture detection module, a control module, and a headrest posture adjustment mechanism. Noise reduction modules are provided on both the headrest side wings and the headrest body. The control headrest posture detection module collects the passenger's head image corresponding to the car headrest, and analyzes and processes it to obtain the spatial position information and posture angle information of the passenger's head relative to the headrest side wings and the headrest body; The headrest target offset information is determined based on spatial location information and attitude angle information; wherein, the headrest target offset information is obtained from the actual position information of the passenger on the headrest side wing and headrest body, the historical position information of the previous collection cycle, and / or the position information predicted by the passenger on the headrest side wing and headrest body corresponding to the preset collection cycle. The headrest posture adjustment mechanism is controlled to adjust the current headrest posture information based on the headrest target offset information; and the noise reduction module is used to reduce the noise of the current headrest.

2. The noise reduction method for a car headrest according to claim 1, characterized in that, The headrest target offset information is determined based on spatial location information and attitude angle information, including: Acquire the actual spatial location information and actual attitude angle information corresponding to the current acquisition cycle; Obtain the first mapping relationship between the head coordinate system and the headrest coordinate system, where the spatial position information and posture angle information are located; The corresponding actual position information is determined based on the actual spatial position information, the actual attitude angle information, and the first mapping relationship; Obtain the historical spatial location information and historical attitude angle information corresponding to the previous acquisition cycle of the current acquisition cycle; The corresponding historical location information is determined based on historical spatial location information, historical attitude angle information, and the first mapping relationship; The headrest target offset information is determined based on the actual location information and the historical location information.

3. The noise reduction method for a car headrest according to claim 2, characterized in that, The corresponding actual position information is determined based on the actual spatial position information, the actual attitude angle information, and the first mapping relationship, including: With the geometric center point of the headrest body as the origin, a headrest coordinate system is established along the horizontal, longitudinal and vertical directions of the vehicle, and the boundary coordinates of the headrest body and the opening and closing boundary coordinates of the headrest side wings are marked to form the spatial range of the vehicle headrest. A head coordinate system is established with the geometric center of the passenger's head as the origin, along the left-right direction, the front-back direction, and the vertical direction of the passenger's head. The first coordinate information of the head coordinate system, which contains the actual spatial location information and the actual posture angle information, is transformed to the headrest coordinate system to obtain the second coordinate information; The first relative position information between the passenger's head and the headrest body is determined based on the origin information and spatial area range corresponding to the second coordinate information. The second relative position information between the passenger's ear and the headrest side wings is determined based on the second coordinate information of the headrest coordinate system where the actual posture angle information is located; The actual location information is determined based on the first relative location information and the second relative location information.

4. The noise reduction method for a car headrest according to claim 1, characterized in that, The headrest target offset information is determined based on spatial location information and attitude angle information, including: Based on the current acquisition cycle, obtain the historical spatial location information and historical attitude angle information corresponding to the preset acquisition cycle; Obtain the first mapping relationship between the head coordinate system and the headrest coordinate system for each historical spatial location information and each historical posture angle information; The corresponding historical location information is determined based on each historical spatial location information, each historical attitude angle information, and the first mapping relationship; Head movement trend information is obtained by performing trend fitting processing based on historical location information. The head target position information is predicted based on head movement trend information; The headrest target offset information is determined based on the head target position information and the current position information.

5. The noise reduction method for a car headrest according to claim 4, characterized in that, Head movement trend information is obtained by trend fitting based on historical location information, including: The first change direction and the first change rate are determined based on the historical attitude angle information. If the first direction of change is the same within multiple consecutive sampling periods, and the first rate of change is greater than a preset speed, then the trend direction corresponding to the head movement trend information is determined. Based on historical location information, information fitting processing is performed to obtain motion information corresponding to head movement trend information; The head movement trend information is determined based on the trend direction and the movement information.

6. The noise reduction method for a car headrest according to claim 4, characterized in that, After obtaining head movement trend information through trend fitting based on historical location information, the process also includes: A behavioral habit rule base corresponding to passengers is obtained in advance, wherein the behavioral habit rule base is extracted by clustering various behavioral habits; The first correction parameter is obtained by matching the habit rule base with the passenger's historical behavior habits. The head movement trend information is corrected according to the first correction parameter to obtain new head movement trend information, so as to proceed to the step of predicting the head target position information based on the head movement trend information.

7. The noise reduction method for a car headrest according to claim 4, characterized in that, After obtaining head movement trend information through trend fitting based on historical location information, the process also includes: A micro-expression motion rule base corresponding to the passenger is obtained in advance, wherein the micro-expression motion rule base is obtained through the mapping relationship between each eye micro-expression, spatial position information and posture angle information; The second correction parameter is obtained by matching the micro-expression movement rule library with the passenger's historical eye micro-expressions; The head movement trend information is corrected according to the second correction parameter to obtain new head movement trend information, so as to proceed to the step of predicting the head target position information based on the head movement trend information.

8. The noise reduction method for a car headrest according to claim 4, characterized in that, After obtaining head movement trend information through trend fitting based on historical location information, the process also includes: A road condition motion rule base for passengers under road condition events is obtained in advance, wherein the road condition motion rule base is obtained by extracting the motion information of passengers' heads under each road condition event; Pre-set the car navigation system to execute warnings for various historical road condition events ahead; The third correction parameter is obtained by matching the road condition movement rule base with historical road condition events; The head movement trend is corrected based on the third correction parameter and the warning execution operation information to obtain new head movement trend information, so as to proceed to the step of predicting the head target position information based on the head movement trend information.

9. The noise reduction method for a car headrest according to any one of claims 1 to 8, characterized in that, The noise reduction module is used to reduce noise in the current headrest environment, including: The relative positional deviation between the noise reduction module of the current headrest and the passenger's ear is determined based on the headrest target offset information; wherein, the relative positional deviation includes distance positional deviation, angle positional deviation and comprehensive positional deviation; The distance position deviation, the angle position deviation, and the comprehensive position deviation are compared with their respective thresholds to determine the corresponding noise reduction strategies. The noise at the current headrest is processed according to each noise reduction strategy; Correspondingly, the process of determining the noise reduction strategy includes: If the distance position deviation is greater than 0, the acoustic gain is increased to compensate for the energy attenuation during the propagation of the acoustic wave; if the distance position deviation is less than 0, the acoustic gain is reduced, and the howling frequency is filtered by notch filtering according to the howling suppression strategy. If the angular position deviation is not equal to 0, the phase modulation of the noise reduction module is adjusted to correct the main lobe direction of the sound wave beam to the direction of the ear canal, and multiple microphones on the side of the headrest are used to collect the noise around the ear to obtain the noise spectrum, thereby achieving noise reduction processing. If the overall position deviation is greater than 1, the mapping relationship between historical offset and noise reduction parameters is invoked, the target parameter is matched according to the mapping relationship, and noise reduction processing is performed according to the target parameter.

10. A car headrest, characterized in that, It includes a head posture detection module, a control module, and a headrest posture adjustment mechanism, and both the headrest side wings and the headrest body are equipped with noise reduction modules; The headrest posture detection module, the control module, and the headrest posture adjustment mechanism are connected in sequence; the noise reduction module is connected to the control module. The headrest posture detection module is used to collect the passenger's head image corresponding to the car headrest, and analyze and process it to obtain the spatial position information and posture angle information of the passenger's head relative to the headrest side wings and the headrest body. The control module is used to execute the steps of the noise reduction method for the car headrest according to any one of claims 1 to 9, so as to achieve noise reduction processing.

Images