Head motion determination method, apparatus, device, and storage medium

Abstract

This application discloses a method, apparatus, device, and storage medium for determining head movements, relating to the field of head-mounted device technology. The method includes: converting initial angular velocity data collected by a gyroscope to a target coordinate system to obtain target angular velocity data; determining the target temporal features corresponding to the target angular velocity data, wherein the target temporal features include at least one of a first temporal feature corresponding to the first angular velocity data, a second temporal feature corresponding to the second angular velocity data, and a third temporal feature corresponding to the third angular velocity data; and matching the target temporal features with preset temporal features corresponding to each type of head movement to determine the target head movement type. Therefore, by extracting the temporal features of each of the three-axis angular velocity data and matching them with preset temporal features corresponding to various head movements, the detailed differences in head movements can be comprehensively captured, significantly improving the accuracy of head movement recognition and reducing the false recognition rate of similar movements.

Description

Technical Field

[0001] This application relates to the field of head-mounted device technology, and more particularly to head motion determination methods, devices, equipment, and storage media. Background Technology

[0002] With the rapid development of head-mounted devices such as wireless headphones, augmented reality / virtual reality headsets, and smart glasses, some of these devices are equipped with methods to detect users' head movements and corresponding operation commands for each head movement. This allows for the operation and control of the head-mounted device by detecting the user's head movements and determining the corresponding operation commands. Therefore, accurately determining head movements based on head-mounted devices has become a key research direction. Summary of the Invention

[0003] The main objective of this application is to provide a method, apparatus, device, and storage medium for determining head movements, aiming to solve the technical problem of how to accurately determine head movements based on a head-mounted device.

[0004] To achieve the above objectives, this application proposes a head motion determination method applied to a head-mounted device, wherein the head-mounted device is equipped with a gyroscope, and the method includes: The initial angular velocity data collected by the gyroscope is transformed into the target coordinate system to obtain the target angular velocity data. The origin of the target coordinate system is the midpoint between the two ears of the head. The first axis is on the straight line where the two ears of the head are located, the second axis is on the straight line where the neck is located, and the third axis is perpendicular to the first axis and the second axis. The target angular velocity data includes the first angular velocity data corresponding to the first axis, the second angular velocity data corresponding to the second axis, and the third angular velocity data corresponding to the third axis. Determine the target time-domain features corresponding to the target angular velocity data, wherein the target time-domain features include at least one of the first time-domain features corresponding to the first angular velocity data, the second time-domain features corresponding to the second angular velocity data, and the third time-domain features corresponding to the third angular velocity data; The target temporal features are matched with preset temporal features corresponding to each head movement type to determine the target head movement type.

[0005] Furthermore, to achieve the above objectives, this application also proposes a head motion determination device, disposed in a head-mounted device, wherein the head-mounted device is equipped with a gyroscope, and the head motion determination device includes: The conversion module is used to convert the initial angular velocity data collected by the gyroscope to the target coordinate system to obtain target angular velocity data. The origin of the target coordinate system is the midpoint between the two ears of the head. The first axis is on the straight line where the two ears of the head are located, the second axis is on the straight line where the neck is located, and the third axis is perpendicular to the first axis and the second axis. The target angular velocity data includes the first angular velocity data corresponding to the first axis, the second angular velocity data corresponding to the second axis, and the third angular velocity data corresponding to the third axis. The first determining module is used to determine the target time-domain features corresponding to the target angular velocity data, wherein the target time-domain features include at least one of the first time-domain features corresponding to the first angular velocity data, the second time-domain features corresponding to the second angular velocity data, and the third time-domain features corresponding to the third angular velocity data. The second determining module is used to match the target temporal features with the preset temporal features corresponding to each head movement type to determine the target head movement type.

[0006] In addition, to achieve the above objectives, this application also proposes a head motion determination device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the head motion determination method as described above.

[0007] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the head motion determination method described above.

[0008] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the head motion determination method described above. Attached Figure Description

[0009] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0010] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a flowchart illustrating an embodiment of the head motion determination method of this application. Figure 2 This is a flowchart illustrating Embodiment 2 of the head motion determination method of this application. Figure 3 This is a waveform diagram corresponding to a first action type provided in an embodiment of the present disclosure; Figure 4 This application provides a waveform diagram corresponding to a head swing. Figure 5 This application provides a waveform diagram corresponding to head shaking; Figure 6 This is a flowchart illustrating Embodiment 3 of the head motion determination method of this application; Figure 7 This is a schematic diagram of the module structure of the head motion determination device according to an embodiment of this application; Figure 8 This is a schematic diagram of the device structure of the hardware operating environment involved in the head motion determination method in the embodiments of this application.

[0012] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0013] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0014] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0015] The Inertial Measurement Unit (IMU) is the key sensor for motion sensing and attitude recognition. The core components of the IMU include a three-axis accelerometer and a three-axis gyroscope. The accelerometer measures the linear acceleration of the head-mounted device in three-dimensional space, while the gyroscope measures the angular velocity (i.e., rotation rate) of the headphones about three orthogonal axes. By fusing high-frequency, high-precision data from these two types of sensors in real time, the IMU can accurately capture the user's head motion (such as movement and rotation) and spatial orientation (i.e., attitude), providing a solid data foundation for head posture-based intelligent interaction.

[0016] The rapid development of information technology has led to the deep penetration of smart terminal devices (such as smartphones, smartwatches, wireless headphones, augmented reality / virtual reality headsets, smart glasses, and in-vehicle infotainment systems) into people's daily lives and work. This has resulted in a significant increase in user demand for natural, efficient, convenient, and contactless human-computer interaction. However, in many key scenarios, traditional interaction methods face severe challenges.

[0017] Hand-restricted scenarios: In scenarios such as driving, cycling, carrying heavy objects, surgery, precision laboratory operations, and industrial production lines, users' hands are heavily occupied, making touchscreen or precise button operations impossible, necessitating hands-free interaction solutions. Privacy and silence scenarios: In meetings, libraries, quiet hospital wards, or noisy environments, voice control fails due to disturbing others, privacy breaches, or environmental noise interference, requiring silent interaction methods. Accessibility scenarios: For users with limited physical mobility, traditional hand-based interaction methods present inherent barriers, urgently requiring alternative and inclusive control methods. Immersive experience scenarios: In virtual worlds built with augmented reality / virtual reality, relying on controllers, buttons, or frequent voice commands disrupts immersion; users expect more intuitive physical actions as input.

[0018] Currently, the mainstream interaction methods for smart terminals are touchscreens, physical buttons, gesture tapping (such as tap control in wireless headphones), and voice. All of these methods exhibit significant shortcomings in various scenarios: Touchscreens and buttons: heavily reliant on hand operation, making them virtually unusable in "hand-restricted scenarios" and "accessible scenarios." Tapping / touch control: while partially freeing up visual attention, still requires precise finger movements, making it difficult and prone to accidental triggering in dynamic environments (such as sports or driving) or when wearing gloves, and similarly failing to address hand-restricted issues. Voice control: performs poorly in "privacy and silence scenarios" and high-noise environments, and suffers from wake-up delays, accent recognition issues, and privacy concerns, limiting its universality.

[0019] Therefore, exploring new interaction paradigms based on users' natural body movements has become a key direction to meet the above-mentioned urgent needs. Among them, using head posture for recognition and interaction shows unique application potential: (1) Naturalness and universality: Head movement is one of the most natural actions for humans to express their intentions (such as nodding to confirm, shaking their head to refuse, and looking around), without the need for additional learning costs. (2) Non-contact and freeing up hands: It completely eliminates hand dependence and achieves control through non-contact methods, perfectly meeting the core demand of "hand-restricted scenarios". (3) Silence and privacy protection: Silent operation avoids the embarrassment and risks of voice interaction in "privacy and silence scenarios". (4) Enhanced immersion: In augmented reality / virtual reality, head posture is the core input for building spatial perception and navigation. As a source of control commands, it can significantly improve the naturalness and immersion of the interaction. (5) Assistive function potential: It provides an intuitive and feasible alternative control channel for users with physical disabilities.

[0020] In conclusion, given the current industry situation where traditional interaction methods (especially physical buttons, tapping, and voice) face bottlenecks in the aforementioned scenarios, developing high-precision, low-latency, and robust head posture recognition and interaction technologies is not only of significant practical importance but also holds immense application value. It represents a key breakthrough in improving the universality of smart terminals and enhancing user experience.

[0021] Therefore, this application provides a solution to transform the initial angular velocity data collected by the gyroscope into a target coordinate system to obtain target angular velocity data. The origin of the target coordinate system is the midpoint between the two ears of the head. The first axis is on the straight line where the two ears of the head are located, the second axis is on the straight line where the neck is located, and the third axis is perpendicular to the first axis and the second axis. The target angular velocity data includes the first angular velocity data corresponding to the first axis, the second angular velocity data corresponding to the second axis, and the third angular velocity data corresponding to the third axis. Then, the temporal features corresponding to the target angular velocity data are determined. The target temporal features include at least one of the first temporal features corresponding to the first angular velocity data, the second temporal features corresponding to the second angular velocity data, and the third temporal features corresponding to the third angular velocity data. Finally, the target temporal features are matched with the preset temporal features corresponding to each type of head movement to determine the target head movement type.

[0022] As can be seen from the above embodiments, by converting the initial angular velocity data collected by the gyroscope to a target coordinate system that is compatible with the physiological structure of the human head, the recognition interference caused by the device wearing angle deviation can be effectively eliminated, and the converted three-axis angular velocity data can accurately map the actual head activity state. At the same time, by extracting the temporal domain features of each of the three-axis angular velocity data and matching them with the preset temporal domain features corresponding to various head movements, the detailed differences of head movements can be fully captured, greatly improving the accuracy of head movement recognition and reducing the misidentification rate of similar movements.

[0023] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, mobile phone, head-mounted device, etc., or an electronic device or head motion determination device capable of performing the above functions. The following description uses a head motion determination device as an example to illustrate this embodiment and the subsequent embodiments.

[0024] Based on this, embodiments of this application provide a method for determining head movements, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the head motion determination method of this application. Figure 1 As shown, the head movement determination method includes steps S10 to S40: Step S10: Convert the initial angular velocity data collected by the gyroscope to the target coordinate system to obtain the target angular velocity data.

[0025] The initial angular velocity data is the raw head rotation angular velocity data directly collected by the gyroscope in its own hardware coordinate system without coordinate transformation.

[0026] The target coordinate system is a dedicated coordinate system adapted to the physiological structure and movement characteristics of the human head. The origin of the target coordinate system is the midpoint between the two ears on the head. The first axis of the target coordinate system is on the straight line where the two ears are located. The second axis of the target coordinate system is on the straight line where the neck is located. The third axis of the target coordinate system is perpendicular to the first axis and the second axis.

[0027] Among them, the target angular velocity data is the angular velocity data that corresponds one-to-one with the three axes of the target coordinate system after the initial angular velocity data is transformed, and can directly represent the rotational motion state of the head in different dimensions.

[0028] The target angular velocity data includes the first angular velocity data corresponding to the first axis, the second angular velocity data corresponding to the second axis, and the third angular velocity data corresponding to the third axis.

[0029] In one possible implementation, the Euler angular coordinate transformation algorithm can be used to rotate and transform the initial angular velocity data of the gyroscope hardware coordinate system according to the three-axis spatial angular relationship of the target coordinate system to obtain the target angular velocity data.

[0030] In another possible implementation, the initial angular velocity data is mapped to spatial coordinates based on the quaternion coordinate transformation method to generate triaxial angular velocity data in the target coordinate system.

[0031] Step S20: Determine the target time-domain characteristics corresponding to the target angular velocity data.

[0032] The target time-domain features include at least one of the first time-domain features corresponding to the first angular velocity data, the second time-domain features corresponding to the second angular velocity data, and the third time-domain features corresponding to the third angular velocity data.

[0033] Among them, time-domain features are feature parameters extracted from the target angular velocity data through analysis in the time dimension, reflecting the variation of angular velocity over time. Optionally, time-domain features may include maxima, minima, and the first duration between every two adjacent maxima and minima.

[0034] In one possible implementation, a sliding window is used to traverse the first, second, and third angular velocity data, respectively, to extract the maximum, minimum, extreme value sequence, and first duration between any two adjacent extreme values ​​for the first, second, and third angular velocity data within the window, and the second duration between the start time of the time interval and the first extreme value within the time interval. The first duration between adjacent extreme values ​​includes the duration between adjacent maximum and minimum values.

[0035] Step S30: Match the target temporal features with the preset temporal features corresponding to each head movement type to determine the target head movement type.

[0036] Among them, head movement types are movement categories set based on the natural movements of the human head, including nodding, raising head, shaking head, tilting head to the left, tilting head to the right, tilting head to the left, tilting head to the right, etc.

[0037] Among them, the preset time-domain features are typical time-domain feature templates corresponding to each type of head movement, which are obtained through a large number of human head movement experiments and statistical analysis. These templates include standard parameters such as the number of extreme values, the time sequence of extreme values, the range of maximum values, the range of minimum values, and the time interval between two adjacent extreme values.

[0038] Among them, the target head action type is the type of head action actually performed by the user, which is determined after temporal feature matching.

[0039] In one possible implementation, the target temporal feature is matched with each preset temporal feature, and the head action type corresponding to the successfully matched preset temporal feature is determined as the target head action type.

[0040] In this embodiment, by converting the initial angular velocity data collected by the gyroscope to a target coordinate system adapted to the physiological structure of the human head, the recognition interference caused by the device wearing angle deviation can be effectively eliminated, and the converted three-axis angular velocity data can accurately map the actual head activity state. At the same time, by extracting the temporal domain features of each of the three-axis angular velocity data and matching them with the preset temporal domain features corresponding to various head movements, the detailed differences of head movements can be fully captured, greatly improving the accuracy of head movement recognition and reducing the misidentification rate of similar movements.

[0041] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 . Figure 2 This is a flowchart illustrating the second embodiment of the head motion determination method of this application, as shown below. Figure 2 As shown, step S20 also includes steps S21 to S23: Step S21: If the absolute value of the angular velocity at the first moment in the first angular velocity data is greater than the first angular velocity threshold, determine the first time domain feature corresponding to the first angular velocity data within the first time period, wherein the first time period is the time period corresponding to the first preset duration after the first moment.

[0042] The first moment is the point in time when the absolute value of the first angular velocity data first crosses the first angular velocity threshold, indicating that the head has an effective rotational motion in the dimension corresponding to the first axis, rather than random shaking.

[0043] The first angular velocity threshold is an angular velocity threshold set based on the biomechanical characteristics of human head movements. It is higher than the angular velocity of random shaking and lower than the angular velocity of violent and invalid movements. It is used to filter valid head movements in the first axis dimension and eliminate invalid interference.

[0044] The first preset duration can be set based on the periodic characteristics of the head movement corresponding to the first axis. For example, the nodding period is about 0.3 seconds to 1.2 seconds, which ensures that the temporal characteristics of a valid movement can be captured completely.

[0045] In one possible implementation, multiple nodding and head-raising operations by the wearable device user can be acquired, and a first preset duration and a first angular velocity threshold can be determined through statistical analysis.

[0046] In one possible implementation, the absolute value of the first angular velocity data is monitored in real time. When the value first exceeds the first angular velocity threshold, the time point is recorded as the first moment, and timing is started. Timing stops when the timing reaches the first preset duration, and the first time domain feature of the first angular velocity data within that time period is extracted.

[0047] In one possible implementation, the target time-domain feature includes a maximum value, a minimum value, a first duration between any two adjacent maximum and minimum values, and a second duration between the start time of the time period and the first extreme value within the time period. Therefore, the first time-domain feature includes the first maximum value, the first minimum value, the first duration between any two adjacent maximum and minimum values ​​of the first angular velocity data within the first time period, and the second duration between the first moment and the first extreme value within the first time period.

[0048] Step S22: If the absolute value of the angular velocity at the second moment in the second angular velocity data is greater than the second angular velocity threshold, determine the second time domain feature corresponding to the second angular velocity data within the second time period, wherein the second time period is the time period corresponding to the second preset duration after the second moment.

[0049] The second moment is the point in time when the absolute value of the second angular velocity data first crosses the second angular velocity threshold, marking the effective rotational motion of the head in the dimension corresponding to the second axis.

[0050] The second angular velocity threshold is an angular velocity threshold set for the head shaking and swaying motions corresponding to the second axis. The second angular velocity threshold must be less than the head shaking angular velocity, such as 50-200 degrees / second (° / s). The second angular velocity threshold is also higher than the angular velocity of small swaying, so as to filter out effective head shaking and swaying motions.

[0051] The second preset duration can be set based on the periodic characteristics of the head movement (e.g., head shaking) corresponding to the second axis. For example, the head shaking period is approximately 0.5 to 3 seconds, ensuring that the temporal characteristics of a valid movement can be captured completely.

[0052] In one possible implementation, multiple head-shaking operations by the wearable device user can be acquired, and a second preset duration and a second angular velocity threshold can be determined through statistical analysis.

[0053] In one possible implementation, the absolute value of the second angular velocity data is monitored in real time. When the value first exceeds the second angular velocity threshold, the time point is recorded as the second moment, and timing is started. Timing stops when the timing reaches the second preset duration, and the second time domain feature of the second angular velocity data within this time period is extracted.

[0054] In one possible implementation, the target time-domain feature includes a maximum value, a minimum value, a first duration between any two adjacent maximum and minimum values, and a second duration between the start time of the time period and the first extreme value within the time period. Then, the second time-domain feature includes the second maximum value, the second minimum value, the first duration between any two adjacent maximum and minimum values ​​of the second angular velocity data within the second time period, and the second duration between the second moment and the first extreme value within the second time period.

[0055] Step S23: If the absolute value of the angular velocity at the third moment in the third angular velocity data is greater than the third angular velocity threshold, determine the third time domain feature corresponding to the third angular velocity data within the third time period, wherein the third time period is the time period corresponding to the third duration after the third moment.

[0056] The third moment is the point in time when the absolute value of the third angular velocity data first crosses the third angular velocity threshold, marking the effective rotational motion of the head in the dimension corresponding to the third axis.

[0057] The third angular velocity threshold is an angular velocity threshold set for the head tilting motion corresponding to the third axis. The third angular velocity threshold must be less than the head tilting angular velocity, such as 50-150 degrees / second (° / s). The third angular velocity threshold must also be higher than the angular velocity of a slight sway, so as to filter out effective head tilting motions.

[0058] The third duration can be set based on the periodic characteristics of the head movement (e.g., head tilt) corresponding to the third axis. For example, the head tilt period is approximately 0.5 to 2 seconds, ensuring that the temporal characteristics of a valid movement can be captured completely.

[0059] In one possible implementation, multiple left and right head tilting operations by the wearable device user can be acquired, and the third duration and third angular velocity thresholds can be determined through statistical analysis.

[0060] In one possible implementation, the absolute value of the third angular velocity data is monitored in real time. When the value first exceeds the third angular velocity threshold, the time point is recorded as the third moment, and timing is started. Timing stops when the third duration is reached, and the third time-domain features of the third angular velocity data within that time period are extracted.

[0061] In one possible implementation, the target time-domain feature includes a maximum value, a minimum value, a first duration between any two adjacent maximum and minimum values, and a second duration between the start time of the time period and the first extreme value within the time period. Then, the second time-domain feature includes the third maximum value, the third minimum value, the first duration between any two adjacent maximum and minimum values ​​of the third angular velocity data within the third time period, and the second duration between the third time point and the first extreme value within the third time period.

[0062] In this embodiment, specific angular velocity threshold triggering conditions and feature extraction time periods are set for the angular velocity data of the three axes of the target coordinate system. Only when the absolute value of the angular velocity of each axis crosses the corresponding threshold is the temporal feature of that axis extracted within a fixed time period. This effectively eliminates the interference of invalid noise such as random head shaking and slight swaying through threshold screening, and ensures the integrity and relevance of temporal features of various head movements by setting extraction time periods for each axis. At the same time, it avoids meaningless feature extraction throughout the entire time period. This improves the accuracy of feature extraction while further reducing the power consumption of computation, laying a high-quality feature data foundation for accurate head movement matching in the future.

[0063] like Figure 2 As shown, step S30 may further include steps S31 to S33: Step S31: Match the first time domain feature with the preset time domain feature corresponding to the first action type to determine the target head action type, wherein the first action type includes nodding and / or raising head.

[0064] Among them, the first action type is the head action type corresponding to the first axis of the target coordinate system, namely nodding and raising the head, which is essentially the rotational movement of the head around the horizontal axis.

[0065] Among them, the preset time domain features corresponding to the first action type can be typical time domain feature templates collected from a large number of nodding and head-raising action experiments, including standard parameters such as the number of extreme values, extreme value sequence, and action cycle, such as the symmetrical cycle of "first forward rotation, then reverse rotation" for nodding and the action duration of 0.3-1.5s.

[0066] It should be noted that matching the first action type with the exclusive temporal features of the first axis can achieve independent recognition of actions in different dimensions, avoid interference between different head movements, and improve the overall accuracy and efficiency of recognition.

[0067] In one possible implementation, the positive direction of the first axis is toward the right side of the head. If the first extreme value in the first time period is the minimum value, there are two first maximum values ​​and two first minimum values ​​in the first time period, and the first time domain feature matches the preset time domain feature corresponding to the nodding, then the target head action type is determined to be nodding.

[0068] In another possible implementation, if the positive direction of the first axis is towards the left side of the head, the first extreme value in the first time period is a maximum value, there are two first minimum values ​​and two first maximum values ​​in the first time period, and the first time domain feature matches the preset time domain feature corresponding to the nodding, then the target head action type is determined to be nodding.

[0069] In a specific implementation, if the two first minimum values ​​in the first time domain feature are within the minimum range corresponding to the nod, the two first maximum values ​​are within the maximum range corresponding to the nod, the first duration is within the first duration range corresponding to the nod, and the second duration is within the second duration range corresponding to the nod, then the first time domain feature is determined to match the preset time domain feature corresponding to the nod, and the target head action type is determined to be a nod.

[0070] Specifically, if the positive direction of the first axis is towards the right side of the head, the first duration range corresponding to the nodding includes the duration range between the first minimum and the first maximum, the duration range between the first maximum and the second minimum, and the duration range between the second minimum and the second maximum. If the positive direction of the first axis is towards the left side of the head, the first duration range corresponding to the nodding includes the duration range between the first maximum and the first minimum, the duration range between the first minimum and the second maximum, and the duration range between the second maximum and the second minimum.

[0071] Figure 3 This is a waveform diagram corresponding to a first action type provided in an embodiment of the present disclosure; when the positive direction of the first axis is toward the left side of the head, Figure 3 This is a waveform diagram corresponding to two nods. It includes two first maxima and two first minima, with the first extremum being a maximum.

[0072] It should be noted that double nodding can more accurately determine whether the user has performed the nodding action, avoiding misjudgment.

[0073] In some embodiments, multiple nodding operations by a wearable device user can be acquired, and statistical analysis can be used to determine a first duration range and a second duration range corresponding to the head-raising.

[0074] In another possible implementation, the positive direction of the first axis is toward the right side of the head. If the first extreme value in the first time period is a maximum value, there are two first maximum values ​​and two first minimum values ​​in the first time period, and the first time domain feature matches the preset time domain feature corresponding to head tilting, then the target head movement type is determined to be head tilting.

[0075] It should be noted that when the positive direction of the first axis is towards the right side of the head, Figure 3 This is a waveform diagram corresponding to two head-up movements, which includes two first maxima and two first minima, with the first extremum being a maximum.

[0076] In another possible implementation, the positive direction of the first axis is towards the left side of the head. If the first extreme value in the first time period is the minimum value, there are two first minimum values ​​and two first maximum values ​​in the first time period, and the first time domain feature matches the preset time domain feature corresponding to head tilting, then the target head movement type is determined to be head tilting.

[0077] In a specific implementation, if the two first minimum values ​​in the first time domain feature are within the minimum range corresponding to head tilting, the two first maximum values ​​are within the maximum range corresponding to head tilting, the first duration is within the first duration range corresponding to head tilting, and the second duration is within the second duration range corresponding to head tilting, then the first time domain feature is determined to match the preset time domain feature corresponding to head tilting, and the target head movement type is determined to be head tilting.

[0078] Wherein, if the positive direction of the first axis is towards the right side of the head, the first duration range corresponding to looking up may include at least one of the duration range between the first maximum and the first minimum, the duration range between the first minimum and the second maximum, and the duration range between the second maximum and the second minimum.

[0079] In some embodiments, multiple head-up actions by a wearable device user can be acquired, and statistical analysis can be used to determine a first duration range and a second duration range corresponding to the head-up actions.

[0080] Step S32: Match the second time domain feature with the preset time domain feature corresponding to the second action type to determine the target head action type, wherein the second action type includes at least one of head shaking, left head shaking, and right head shaking.

[0081] The second action type is the head action type corresponding to the second axis of the target coordinate system, namely head shaking, left head shaking, and right head shaking.

[0082] Among them, the preset time-domain features corresponding to the second action type can be typical time-domain feature templates collected based on a large number of head-shaking action experiments.

[0083] It should be noted that matching the second action type with the exclusive temporal features based on the second axis can achieve independent recognition of actions in different dimensions, avoid interference between different head movements, and improve the overall accuracy and efficiency of recognition.

[0084] In one possible implementation, the positive direction of the second axis points to the top of the head. If the first extreme value in the second time period is a maximum value, there is a second maximum value and a second minimum value in the second time period, and the second time domain feature matches the preset time domain feature corresponding to the left head swing, then the target head movement type is determined to be a left head swing.

[0085] In another possible implementation, the positive direction of the second axis is the opposite direction to the top of the head. If the first extreme value in the second time period is the minimum value, there is a second minimum value and a second maximum value in the second time period, and the second time domain feature matches the preset time domain feature corresponding to the left head swing, then the target head movement type is determined to be a left head swing.

[0086] In a specific implementation, if a second maximum value in the second time domain feature is within the maximum range corresponding to the left head swing, a second minimum value is within the minimum range corresponding to the left head swing, the first duration is within the first duration range corresponding to the left head swing, and the second duration is within the second duration range corresponding to the left head swing, then the second time domain feature is determined to match the preset time domain feature corresponding to the left head swing, and the target head movement type is determined to be a left head swing.

[0087] In some embodiments, multiple left head-shaking operations by a wearable device user can be acquired, and through statistical analysis, a first duration range and a second duration range corresponding to the left head-shaking can be determined.

[0088] In one possible implementation, the positive direction of the second axis points to the top of the head. If the first extreme value in the second time period is the minimum value, there is a second maximum value and a second minimum value in the second time period, and the second time domain feature matches the preset time domain feature corresponding to the right head swing, then the target head movement type is determined to be a right head swing.

[0089] In another possible implementation, the positive direction of the second axis is the opposite direction to the top of the head. If the first extreme value in the second time period is a maximum value, there is a second maximum value and a second minimum value in the second time period, and the second time domain feature matches the preset time domain feature corresponding to the right head swing, then the target head movement type is determined to be a right head swing.

[0090] In a specific implementation, if a second maximum value in the second time domain feature is within the maximum range corresponding to the right head swing, a second minimum value is within the minimum range corresponding to the right head swing, the first duration is within the first duration range corresponding to the right head swing, and the second duration is within the second duration range corresponding to the right head swing, then the second time domain feature is determined to match the preset time domain feature corresponding to the right head swing, and the target head movement type is determined to be a right head swing.

[0091] In some embodiments, multiple right head-shaking operations by a wearable device user can be acquired, and a first duration range and a second duration range corresponding to the right head-shaking can be determined through statistical analysis.

[0092] Figure 4 A waveform diagram corresponding to a head swing provided in this application is shown below. Figure 4 As shown, the head swing contains a maximum and a minimum value. If Figure 4 The corresponding positive direction of the second axis is upward. Figure 4 The diagram shown is for the left head swing. If... Figure 4 The corresponding positive direction of the second axis is the opposite direction pointing to the top of the head. Figure 4 The diagram shown is a schematic of the right head swing.

[0093] In one possible implementation, if there are two second maxima and one second minima in the second time period, and the second time domain feature matches the preset time domain feature corresponding to head shaking, or if there is one second maxima and two second minima in the second time period, and the second time domain feature matches the preset time domain feature corresponding to head shaking, the target head movement type is determined to be head shaking.

[0094] In a specific implementation, if the second maximum value in the second time domain feature is within the maximum range corresponding to head shaking, the second minimum value is within the minimum range corresponding to head shaking, the first duration is within the first duration range corresponding to head shaking, and the second duration is within the second duration range corresponding to head shaking, then the second time domain feature is determined to match the preset time domain feature corresponding to head shaking, and the target head movement type is determined to be head shaking.

[0095] Figure 5 This application provides a waveform diagram corresponding to head shaking. Figure 5 The corresponding positive direction of the second axis points to the top of the head, and the head-shaking motion is to first shake the head to the right and then to the left. If Figure 5 The corresponding positive direction of the second axis is the opposite direction of the top of the head, and the head-shaking action is to first shake the head to the left and then to the right.

[0096] In some embodiments, multiple head-shaking operations by a wearable device user can be acquired, and statistical analysis can be used to determine a first duration range and a second duration range corresponding to the head-shaking.

[0097] Step S33: Match the third time domain feature with the preset time domain feature corresponding to the third action type to determine the target head action type, wherein the third action type includes tilting the head to the left and / or tilting the head to the right.

[0098] The third action type is the head action type corresponding to the third axis of the target coordinate system, namely, tilting the head to the left and / or tilting the head to the right.

[0099] Among them, the preset temporal features corresponding to the third action type can be typical temporal feature templates collected based on a large number of head tilting action experiments.

[0100] It should be noted that matching the third action type with the exclusive temporal features based on the third axis can achieve independent recognition of actions in different dimensions, avoid interference between different head movements, and improve the overall accuracy and efficiency of recognition.

[0101] In one possible implementation, the positive direction of the third axis points forward of the head. The target head movement type is determined to be a right head tilt when the first extreme value in the third time period is a maximum value, there is a third maximum value and a third minimum value in the third time period, and the third time domain feature matches the preset time domain feature corresponding to the right head tilt.

[0102] In another possible implementation, the direction of the third axis is pointing towards the back of the head. The target head movement type is determined to be a right head tilt when the first extreme value in the third time period is a minimum value, there is a third maximum value and a third minimum value in the third time period, and the third time domain feature matches the preset time domain feature corresponding to the right head tilt.

[0103] In a specific implementation, if the third maximum value in the third time domain feature is within the maximum range corresponding to the right head tilt, the third minimum value is within the minimum range corresponding to the right head tilt, the first duration is within the first duration range corresponding to the right head tilt, and the second duration is within the second duration range corresponding to the right head tilt, then the second time domain feature is determined to match the preset time domain feature corresponding to the right head tilt, and the target head movement type is determined to be a right head tilt.

[0104] In some embodiments, multiple right-tilting operations by a wearable device user can be acquired, and through statistical analysis, a first duration range and a second duration range corresponding to the right-tilting operation can be determined.

[0105] In one possible implementation, the positive direction of the third axis points forward of the head. The target head movement type is determined to be a left head tilt when the first extreme value in the third time period is a minimum value, there is a third maximum value and a third minimum value in the third time period, and the third time domain feature matches the preset time domain feature corresponding to the left head tilt.

[0106] In another possible implementation, the direction of the third axis is pointing towards the back of the head. The target head movement type is determined to be a left head tilt when the first extreme value in the third time period is a maximum value, there is a third maximum value and a third minimum value in the third time period, and the third time domain feature matches the preset time domain feature corresponding to the left head tilt.

[0107] In a specific implementation, if the third maximum value in the third time domain feature is within the maximum range corresponding to the left head tilt, the third minimum value is within the minimum range corresponding to the left head tilt, the first duration is within the first duration range corresponding to the left head tilt, and the second duration is within the second duration range corresponding to the left head tilt, then the second time domain feature is determined to match the preset time domain feature corresponding to the left head tilt, and the target head movement type is determined to be a left head tilt.

[0108] In some embodiments, multiple left-tilting operations by a wearable device user can be acquired, and through statistical analysis, a first duration range and a second duration range corresponding to the left-tilting operation can be determined.

[0109] In this embodiment, the temporal features extracted from the split axis are specifically matched with the head movement types of the corresponding dimensions. The differentiated action matching logic, which corresponds to nodding / raising head, shaking head / tilting head, and tilting head, for the first temporal feature, achieves independent recognition and accurate differentiation of head movements in different dimensions, effectively solving the problem of easy confusion between different head movements. At the same time, the matching judgment is based on the preset temporal feature templates exclusive to each action type, which further improves the robustness and accuracy of recognizing various head movements such as nodding, shaking head, tilting head, and tilting head, and completes the accurate conversion from temporal features to specific head movement types.

[0110] Based on the first embodiment of this application, in the third embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 6 , Figure 6 This is a flowchart illustrating the third embodiment of the head motion determination method of this application, as shown below. Figure 6 As shown, step S10 includes step S11: Step S11: In response to the detection of a preset event, the initial angular velocity data collected by the gyroscope is converted to the target coordinate system to obtain the target angular velocity data.

[0111] Among them, preset events can be triggered by the device in real time when the head-mounted device is in a specific work scenario that requires head movement control. Preset events include incoming calls, music playback, video playback, etc.

[0112] In this embodiment, the gyroscope data coordinate transformation and subsequent head motion recognition process are initiated only when the wearable device detects a preset event. If no event is detected, the gyroscope remains in a low-power state and no data processing is performed.

[0113] like Figure 6 As shown, after step S30, the following steps are also included: Step S40: Based on the target head movement type, control the head-mounted device to respond to the preset event.

[0114] In this embodiment, the corresponding function operation of the head-mounted device can be triggered according to the identified target head movement type to solve the interaction needs corresponding to preset events, such as nodding to answer a call or shaking the head to change songs while playing music.

[0115] In specific implementations, a one-to-one correspondence between target head action types and device function operations can be established based on user habits and device functions.

[0116] For example, when an incoming call is detected and a nodding motion is recognized, the function to answer the call is automatically triggered to respond to the incoming call event; if a head shaking motion is recognized, the function to hang up the call is triggered.

[0117] For example, when the headphones are playing music and a left head tilt is detected, the previous song is skipped; when a right head tilt is detected, the next song is skipped, thus responding to the music playback event.

[0118] In this embodiment, the coordinate transformation and subsequent recognition of gyroscope data are triggered by a preset event, which not only improves power consumption utilization but also avoids accidental touches when there is no need for interaction. At the same time, the identified target head movement type is converted into a targeted functional response of the device to the preset event, so that pure head movement control is accurately matched with the actual use scenario of the device, thereby improving the practicality and universality of head-mounted device interaction.

[0119] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the head motion determination method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0120] This application also provides a head motion determination device, please refer to... Figure 7 The head motion determination device includes: The conversion module 701 is used to convert the initial angular velocity data collected by the gyroscope to the target coordinate system to obtain target angular velocity data. The origin of the target coordinate system is the midpoint between the two ears of the head. The first axis is on the straight line where the two ears of the head are located, the second axis is on the straight line where the neck is located, and the third axis is perpendicular to the first axis and the second axis. The target angular velocity data includes the first angular velocity data corresponding to the first axis, the second angular velocity data corresponding to the second axis, and the third angular velocity data corresponding to the third axis. The first determining module 702 is used to determine the target time-domain features corresponding to the target angular velocity data, wherein the target time-domain features include at least one of the first time-domain features corresponding to the first angular velocity data, the second time-domain features corresponding to the second angular velocity data, and the third time-domain features corresponding to the third angular velocity data. The second determining module 703 is used to match the target time-domain features with the preset time-domain features corresponding to each head movement type to determine the target head movement type.

[0121] In one possible implementation, the second determining module 703 is used for: The first time-domain feature is matched with a preset time-domain feature corresponding to the first action type to determine the target head action type, wherein the first action type includes nodding and / or raising head; The second time-domain feature is matched with the preset time-domain feature corresponding to the second action type to determine the target head action type, wherein the second action type includes at least one of head shaking, left head shaking and right head shaking; The third time-domain feature is matched with the preset time-domain feature corresponding to the third action type to determine the target head action type, wherein the third action type includes tilting the head to the left and / or tilting the head to the right.

[0122] In one possible implementation, the first determining module 702 is used for: If the absolute value of the angular velocity at the first moment in the first angular velocity data is greater than the first angular velocity threshold, the first time domain feature corresponding to the first angular velocity data within the first time period is determined, wherein the first time period is the time period corresponding to the first preset duration after the first moment; If the absolute value of the angular velocity at the second moment in the second angular velocity data is greater than the second angular velocity threshold, the second time-domain feature corresponding to the second angular velocity data within the second time period is determined, wherein the second time period is the time period corresponding to the second preset duration after the second moment; If the absolute value of the angular velocity at the third moment in the third angular velocity data is greater than the third angular velocity threshold, the third time-domain feature corresponding to the third angular velocity data within the third time period is determined, wherein the third time period is the time period corresponding to the third duration after the third moment; The target time-domain features include a maximum value, a minimum value, a first duration between every two adjacent maximum and minimum values, and a second duration between the start time of the time period and the first extreme value within the time period.

[0123] In one possible implementation, the second determining module 703 is used for: If the first extreme value within the first time period is a minimum value, there are two first maximum values ​​and two first minimum values ​​within the first time period, and the first temporal feature matches the preset temporal feature corresponding to the nodding, then the target head movement type is determined to be a nodding; or... If the first extreme value in the first time period is a maximum value, there are two first maximum values ​​and two first minimum values ​​in the first time period, and the first time domain feature matches the preset time domain feature corresponding to head tilting, then the target head movement type is determined to be head tilting.

[0124] In one possible implementation, the second determining module 703 is used for: If the first extreme value in the second time period is a maximum value, there is a second maximum value and a second minimum value in the second time period, and the second time domain feature matches the preset time domain feature corresponding to the left head swing, then the target head movement type is determined to be a left head swing. If the first extreme value in the second time period is the minimum value, there is a second maximum value and a second minimum value in the second time period, and the second time domain feature matches the preset time domain feature corresponding to the right head swing, then the target head movement type is determined to be a right head swing. If, within the second time period, there are two second maxima and one second minima, and the second time-domain feature matches the preset time-domain feature corresponding to head shaking, or if, within the second time period, there is one second maxima and two second minima, and the second time-domain feature matches the preset time-domain feature corresponding to head shaking, then the target head movement type is determined to be head shaking.

[0125] In one possible implementation, the second determining module 703 is used for: If the first extreme value within the third time period is a maximum value, there is a third maximum value and a third minimum value within the third time period, and the third time-domain feature matches the preset time-domain feature corresponding to the right head tilt, then the target head movement type is determined to be a right head tilt; or... If the first extreme value in the third time period is the minimum value, there is a third maximum value and a third minimum value in the third time period, and the third time domain feature matches the preset time domain feature corresponding to the left head tilt, then the target head movement type is determined to be a left head tilt.

[0126] In one possible implementation, the conversion module 701 is configured to: in response to detecting a preset event, convert the initial angular velocity data collected by the gyroscope to the target coordinate system to obtain target angular velocity data; and further includes a response module configured to: control the head-mounted device to respond to the preset event based on the target head movement type.

[0127] The head motion determination device provided in this application, employing the head motion determination method in the above embodiments, can solve the technical problem of how to accurately determine head motion based on a head-mounted device. Compared with the prior art, the beneficial effects of the head motion determination device provided in this application are the same as those of the head motion determination method provided in the above embodiments, and other technical features in the head motion determination device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0128] This application provides a head motion determination device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the head motion determination method in the first embodiment described above.

[0129] The following is for reference. Figure 8 The diagram illustrates a structural schematic suitable for implementing the head motion determination device in the embodiments of this application. The head motion determination device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 8 The head motion determination device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0130] like Figure 8 As shown, the head motion determination device may include a processing unit 801 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage device 803 into a random access memory (RAM) 804. The RAM 804 also stores various programs and data required for the operation of the head motion determination device. The processing unit 801, ROM 802, and RAM 804 are interconnected via a bus 805. An input / output (I / O) interface 806 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 806: input devices 807 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 808 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 803 including, for example, magnetic tapes, hard disks, etc.; and communication devices 809. Communication device 809 allows the head motion determining device to communicate wirelessly or wiredly with other devices to exchange data. While the figures show head motion determining devices with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0131] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 803, or installed from ROM 802. When the computer program is executed by processing device 801, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0132] The head motion determination device provided in this application, employing the head motion determination method in the above embodiments, can solve the technical problem of how to accurately determine head motion based on a head-mounted device. Compared with the prior art, the beneficial effects of the head motion determination device provided in this application are the same as those of the head motion determination method provided in the above embodiments, and other technical features of this head motion determination device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0133] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0134] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0135] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the head motion determination method in the above embodiments.

[0136] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0137] The aforementioned computer-readable storage medium may be included in the head motion determining device; or it may exist independently and not assembled into the head motion determining device.

[0138] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the head motion determining device, enable the head motion determining device to implement the head motion determining method.

[0139] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0140] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0141] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0142] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described head movement determination method, and can solve the technical problem of how to accurately determine head movements based on a head-mounted device. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the head movement determination method provided in the above embodiments, and will not be repeated here.

[0143] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the head motion determination method described above.

[0144] The computer program product provided in this application can solve the technical problem of how to accurately determine head movements based on a head-mounted device. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the head movement determination method provided in the above embodiments, and will not be repeated here.

[0145] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

[0146] It should be noted that the data collection, tag management, rule setting, and push decision-making processes involved in this application are designed to work with other technical features to solve technical problems. They do not involve or support any illegal activities. Any data processing that may violate laws and regulations (such as unauthorized collection of privacy data, generation of discriminatory tags, setting unfair rules, or pushing illegal information) is not within the scope of protection of this application's technical solution. Of course, the user data in this application will be encrypted, anonymized, or de-identified before storage to ensure user data security.

Claims

1. A method for determining head movements, characterized in that, Applied to a head-mounted device, wherein the head-mounted device is equipped with a gyroscope, the method includes: The initial angular velocity data collected by the gyroscope is transformed into the target coordinate system to obtain the target angular velocity data. The origin of the target coordinate system is the midpoint between the two ears of the head. The first axis is on the straight line where the two ears of the head are located, the second axis is on the straight line where the neck is located, and the third axis is perpendicular to the first axis and the second axis. The target angular velocity data includes the first angular velocity data corresponding to the first axis, the second angular velocity data corresponding to the second axis, and the third angular velocity data corresponding to the third axis. Determine the target time-domain features corresponding to the target angular velocity data, wherein the target time-domain features include at least one of the first time-domain features corresponding to the first angular velocity data, the second time-domain features corresponding to the second angular velocity data, and the third time-domain features corresponding to the third angular velocity data; The target temporal features are matched with preset temporal features corresponding to each head movement type to determine the target head movement type.

2. The method according to claim 1, characterized in that, The step of matching the target temporal features with preset temporal features corresponding to each head movement type to determine the target head movement type includes: The first time-domain feature is matched with a preset time-domain feature corresponding to the first action type to determine the target head action type, wherein the first action type includes nodding and / or raising head; The second time-domain feature is matched with the preset time-domain feature corresponding to the second action type to determine the target head action type, wherein the second action type includes at least one of head shaking, left head shaking and right head shaking; The third time-domain feature is matched with the preset time-domain feature corresponding to the third action type to determine the target head action type, wherein the third action type includes tilting the head to the left and / or tilting the head to the right.

3. The method according to claim 2, characterized in that, Determining the target time-domain features corresponding to the target angular velocity data includes: If the absolute value of the angular velocity at the first moment in the first angular velocity data is greater than the first angular velocity threshold, the first time domain feature corresponding to the first angular velocity data within the first time period is determined, wherein the first time period is the time period corresponding to the first preset duration after the first moment; If the absolute value of the angular velocity at the second moment in the second angular velocity data is greater than the second angular velocity threshold, the second time-domain feature corresponding to the second angular velocity data within the second time period is determined, wherein the second time period is the time period corresponding to the second preset duration after the second moment; If the absolute value of the angular velocity at the third moment in the third angular velocity data is greater than the third angular velocity threshold, the third time-domain feature corresponding to the third angular velocity data within the third time period is determined, wherein the third time period is the time period corresponding to the third duration after the third moment; The target time-domain features include a maximum value, a minimum value, a first duration between every two adjacent maximum and minimum values, and a second duration between the start time of the time period and the first extreme value within the time period.

4. The method according to claim 3, characterized in that, The positive direction of the first axis is towards the right side of the head. Matching the first temporal feature with a preset temporal feature corresponding to the first action type to determine the target head action type includes: If the first extreme value within the first time period is a minimum value, there are two first maximum values ​​and two first minimum values ​​within the first time period, and the first temporal feature matches the preset temporal feature corresponding to the nodding, then the target head movement type is determined to be a nodding; or... If the first extreme value in the first time period is a maximum value, there are two first maximum values ​​and two first minimum values ​​in the first time period, and the first time domain feature matches the preset time domain feature corresponding to head tilting, then the target head movement type is determined to be head tilting.

5. The method according to claim 3, characterized in that, The positive direction of the second axis points towards the top of the head. Matching the second temporal feature with a preset temporal feature corresponding to the second action type to determine the target head action type includes any one of the following: If the first extreme value in the second time period is a maximum value, there is a second maximum value and a second minimum value in the second time period, and the second time domain feature matches the preset time domain feature corresponding to the left head swing, then the target head movement type is determined to be a left head swing. If the first extreme value in the second time period is the minimum value, there is a second maximum value and a second minimum value in the second time period, and the second time domain feature matches the preset time domain feature corresponding to the right head swing, then the target head movement type is determined to be a right head swing. If, within the second time period, there are two second maxima and one second minima, and the second time-domain feature matches the preset time-domain feature corresponding to head shaking, or if, within the second time period, there is one second maxima and two second minima, and the second time-domain feature matches the preset time-domain feature corresponding to head shaking, then the target head movement type is determined to be head shaking.

6. The method according to claim 3, characterized in that, The positive direction of the third axis points towards the front of the head. Matching the third temporal feature with a preset temporal feature corresponding to the third action type to determine the target head action type includes: If the first extreme value within the third time period is a maximum value, there is a third maximum value and a third minimum value within the third time period, and the third time-domain feature matches the preset time-domain feature corresponding to the right head tilt, then the target head movement type is determined to be a right head tilt; or... If the first extreme value in the third time period is the minimum value, there is a third maximum value and a third minimum value in the third time period, and the third time domain feature matches the preset time domain feature corresponding to the left head tilt, then the target head movement type is determined to be a left head tilt.

7. The method according to any one of claims 1-6, characterized in that, The step of converting the initial angular velocity data collected by the gyroscope to the target coordinate system to obtain the target angular velocity data includes: In response to the detection of a preset event, the initial angular velocity data collected by the gyroscope is converted to the target coordinate system to obtain the target angular velocity data; After matching the target temporal features with preset temporal features corresponding to each head movement type to determine the target head movement type, the method further includes: Based on the target head movement type, the head-mounted device is controlled to respond to the preset event.

8. A head motion determining device, characterized in that, The head movement determination device is installed in a head-mounted device, which includes a gyroscope, and comprises: The conversion module is used to convert the initial angular velocity data collected by the gyroscope to the target coordinate system to obtain target angular velocity data. The origin of the target coordinate system is the midpoint between the two ears of the head. The first axis is on the straight line where the two ears of the head are located, the second axis is on the straight line where the neck is located, and the third axis is perpendicular to the first axis and the second axis. The target angular velocity data includes the first angular velocity data corresponding to the first axis, the second angular velocity data corresponding to the second axis, and the third angular velocity data corresponding to the third axis. The first determining module is used to determine the target time-domain features corresponding to the target angular velocity data, wherein the target time-domain features include at least one of the first time-domain features corresponding to the first angular velocity data, the second time-domain features corresponding to the second angular velocity data, and the third time-domain features corresponding to the third angular velocity data. The second determining module is used to match the target temporal features with the preset temporal features corresponding to each head movement type to determine the target head movement type.

9. A head motion determination device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the head movement determination method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the head motion determination method as described in any one of claims 1 to 7.

Images