Motion monitoring method and system based on head micro-motion and GNSS quality segmentation fusion

Abstract

The application discloses a motion monitoring method and system based on head micro-motion and GNSS quality segmentation fusion, and the method comprises the following steps: acquiring inertial measurement data and GNSS data of a head-mounted device in a motion process; performing attitude alignment and filtering processing on the inertial measurement data to obtain a head micro-motion signal, and extracting periodic characteristics of a current time window based on the head micro-motion signal; determining a step frequency and a period stability of the current time window according to the periodic characteristics, and updating mapping parameters between the step frequency and motion speed according to GNSS speed data; according to GNSS quality data and the period stability, determining a speed calculation state of the current time window as a calibration state, a continuation calculation state or a recovery state; performing smoothing processing on a corrected speed, a continuation calculation speed or a backtracking corrected speed to obtain an output speed, and updating a cumulative motion distance and displaying speed according to the output speed. The application aims to improve the reliability of the cumulative motion distance calculation result and the display result.

Description

Technical Field

[0001] This invention relates to the technical field of motion monitoring methods for smart wearable devices, and particularly to a motion monitoring method, system, computer equipment, and storage medium based on the fusion of head micro-motion and GNSS quality segmentation. Background Technology

[0002] The application of head-mounted devices in motion monitoring is increasing. Real-time monitoring and display of parameters such as speed and distance during user movement using head-mounted devices has become an important development direction for related products. In existing technologies, methods for obtaining motion speed typically include directly determining motion speed based on GNSS data or estimating motion state based on inertial measurement data.

[0003] However, in real-world applications of head-mounted devices, GNSS data is susceptible to factors such as obstruction, multipath effects, and short-term loss of lock, leading to fluctuations, interruptions, or sudden changes in velocity data after recovery. Simultaneously, the inertial measurement data collected by head-mounted devices is also superimposed with unstable motion components such as natural head swaying, causing accumulated estimation errors when relying solely on inertial measurement data for velocity estimation. As a result, existing motion monitoring solutions struggle to consistently obtain accurate, continuous, and stable velocity results during GNSS quality changes, thus affecting the reliability of cumulative distance calculations and display output. Summary of the Invention

[0004] The purpose of this application is to propose a motion monitoring method, system, computer device, and storage medium based on the fusion of head micro-motion and GNSS quality segmentation, so as to solve the technical problem that in the motion monitoring scenario of head-mounted devices, the existing technology is difficult to continuously output motion speed that takes into account accuracy, continuity, and stability during the process of GNSS quality fluctuation, short-term failure, and recovery changes.

[0005] To address the aforementioned technical problems, this application provides a motion monitoring method based on the fusion of head micro-motion and GNSS quality segmentation, employing the following technical solution: Acquire inertial measurement data and GNSS data of the head-mounted device during movement, wherein the GNSS data includes at least GNSS velocity data and GNSS quality data; The inertial measurement data is aligned and filtered to obtain head micro-motion signals, and the periodic features of the current time window are extracted based on the head micro-motion signals. The step frequency and periodic stability of the current time window are determined based on the periodic characteristics, and the mapping parameters between the step frequency and the movement speed are updated based on the GNSS velocity data when the GNSS quality data meets the calibration conditions. Based on the GNSS quality data and the periodic stability, the velocity calculation status of the current time window is determined as calibration status, continuation calculation status, or recovery status. When the velocity calculation state is in calibration state, the corrected velocity is determined based on the GNSS velocity data and the mapping parameters; when the velocity calculation state is in continuation state, the continuation velocity is determined based on the step frequency and the mapping parameters; when the velocity calculation state is in recovery state, the correction amount is determined based on the recovered GNSS velocity data, and the correction amount is allocated according to the periodic stability corresponding to each continuation time window before recovery, so as to perform retrospective correction on the continuation velocity corresponding to the continuation time window before recovery, and obtain the velocity after retrospective correction. The corrected speed, the continued calculation speed, or the backtracked corrected speed are smoothed to obtain the output speed, and the cumulative motion distance and the displayed speed are updated according to the output speed.

[0006] To address the aforementioned technical problems, this application also provides a motion monitoring system based on the fusion of head micro-motion and GNSS quality segmentation, employing the following technical solution: The acquisition module is used to acquire inertial measurement data and GNSS data of the head-mounted device during the movement process, wherein the GNSS data includes at least GNSS velocity data and GNSS quality data; The extraction module is used to perform attitude alignment and filtering on the inertial measurement data to obtain head micro-motion signals, and extract the periodic features of the current time window based on the head micro-motion signals. The first update module is used to determine the step frequency and periodic stability of the current time window based on the periodic characteristics, and update the mapping parameters between the step frequency and the movement speed based on the GNSS velocity data when the GNSS quality data meets the calibration conditions. The determination module is used to determine the velocity calculation status of the current time window as calibration status, continuation calculation status or recovery status based on the GNSS quality data and the periodic stability. When the velocity calculation state is in calibration state, the corrected velocity is determined based on the GNSS velocity data and the mapping parameters; when the velocity calculation state is in continuation state, the continuation velocity is determined based on the step frequency and the mapping parameters; when the velocity calculation state is in recovery state, the correction amount is determined based on the recovered GNSS velocity data, and the correction amount is allocated according to the periodic stability corresponding to each continuation time window before recovery, so as to perform retrospective correction on the continuation velocity corresponding to the continuation time window before recovery, and obtain the velocity after retrospective correction. The second update module is used to smooth the corrected speed, the continued calculation speed, or the backtracked corrected speed to obtain the output speed, and update the cumulative motion distance and the displayed speed according to the output speed.

[0007] To address the aforementioned technical problems, this application also provides a computer device that employs the following technical solution: A computer device includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor executes the computer-readable instructions to implement the steps of the motion monitoring method based on head micro-motion and GNSS quality segment fusion as described above.

[0008] To address the aforementioned technical problems, this application also provides a computer-readable storage medium, employing the technical solution described below: A computer-readable storage medium storing computer-readable instructions, which, when executed by a processor, implement the steps of the motion monitoring method based on head micro-motion and GNSS quality segment fusion as described above.

[0009] Compared with the prior art, the embodiments of this application have the following main advantages: The motion monitoring method disclosed in this application, based on the segmented fusion of head micro-motion and GNSS quality data, simultaneously introduces head micro-motion signals and GNSS quality data to perform segmented fusion processing on velocity calculation during motion. This enables the system to not only calibrate motion velocity using GNSS velocity data when GNSS quality is good, but also to continue calculating velocity based on the motion rhythm reflected by head micro-motion when GNSS quality fluctuates or fails briefly. After GNSS recovers, the continued calculation results are retrospectively corrected. This achieves continuous, accurate, and stable output of motion velocity in complex motion scenarios, further improving the reliability of cumulative motion distance calculation and display results, and enhancing the actual user experience of head-mounted devices in motion monitoring scenarios. Attached Figure Description

[0010] To more clearly illustrate the solutions in this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. 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 of an embodiment of the motion monitoring method based on head micro-motion and GNSS quality segmentation fusion according to this application; Figure 2This is a schematic diagram of a structure of an embodiment of the motion monitoring system based on head micro-motion and GNSS quality segmentation fusion according to this application; Figure 3 This is a schematic diagram of the structure of one embodiment of the computer device according to this application. Detailed Implementation

[0012] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0013] This invention provides a motion monitoring method based on the segmented fusion of head micro-motion and GNSS quality data. It is applicable to smart glasses, sports glasses, head-mounted display terminals, or other head-worn electronic devices, used to continuously monitor movement speed, cumulative distance, and display output during activities such as walking, jogging, and running. This method does not simply rely on GNSS data to directly output speed, nor does it independently calculate speed based solely on inertial measurement data. Instead, it extracts the motion rhythm reflected by head micro-motion signals and segments the speed calculation process in conjunction with GNSS quality changes. This allows it to maintain the continuity, accuracy, and stability of motion monitoring results even in scenarios involving GNSS speed data fluctuations, short-term failures, and recovery. The inertial measurement data here is usually acquired by the accelerometer and gyroscope built into the head-mounted device to reflect the dynamic changes of the head during movement; GNSS data is acquired by the satellite positioning module, where GNSS velocity data is used to characterize the user's current ground movement speed, and GNSS quality data is used to characterize the reliability of GNSS velocity data at the current moment or within the current time window, for example, it can be composed of the number of satellites, the degree of velocity change anomalies, and the discreteness of the velocity sequence.

[0014] refer to Figure 1 The diagram illustrates a flowchart of an embodiment of the motion monitoring method based on head micro-motion and GNSS quality segment fusion according to this application. The motion monitoring method based on head micro-motion and GNSS quality segment fusion includes the following steps: Step S101: Acquire inertial measurement data and GNSS data of the head-mounted device during the movement process, wherein the GNSS data includes at least GNSS velocity data and GNSS quality data.

[0015] In this embodiment, inertial measurement data and GNSS data of the head-mounted device during movement are first acquired to form the dual-source data foundation required for subsequent fusion processing. The reason for simultaneously acquiring these two types of data is that their functions in motion monitoring are clearly complementary. GNSS velocity data can usually directly reflect the user's actual movement speed in open environments, but in scenarios such as tall buildings, tree-lined roads, tunnel entrances, and under bridges, GNSS signals are easily affected by obstruction and multipath effects, resulting in fluctuations, drift, or short-term interruptions. In contrast, while inertial measurement data cannot directly provide ground velocity, it can continuously reflect the rhythmic, minute changes in the user's head as they move with their body. Therefore, it can serve as an important supplementary basis for velocity estimation when GNSS quality deteriorates. For example, when a user is running on a city road wearing smart glasses, GNSS velocity measurements in open areas are usually relatively stable, but when entering areas under overpasses or densely wooded areas, GNSS velocity data may show abrupt changes. At this time, inertial measurement data can still continuously collect the periodic micro-movements of the head generated by gait, providing a basis for subsequent calculations.

[0016] Step S102: The inertial measurement data is aligned and filtered to obtain the head micro-motion signal, and the periodic features of the current time window are extracted based on the head micro-motion signal.

[0017] In this embodiment, after acquiring the raw data, the inertial measurement data undergoes attitude alignment and filtering to obtain head micro-motion signals. The periodic characteristics of the current time window are then extracted based on these head micro-motion signals. Attitude alignment refers to estimating the orientation of the head-mounted device relative to a reference space based on the inertial measurement data, and transforming the acceleration data, originally located in the sensor's body coordinate system, to a unified reference coordinate system related to the direction of gravity. This reduces the impact of different wearing angles and head postures on the signal analysis results. Head micro-motion signals refer to the dynamic signals corresponding to the slight up-and-down and left-and-right swaying of the head during periodic movements such as walking and running, which are produced by the user's head in accordance with the rhythm of the torso and gait. These signals differ from random head swings and sudden head turns, and better reflect the actual movement rhythm. Filtering the inertial measurement data is performed to suppress high-frequency noise, sudden impacts, and low-frequency drift unrelated to the movement rhythm, allowing the retained signals to more concentratedly reflect the periodic change characteristics. Furthermore, periodic features are extracted from the head micro-motion signals within the current time window. The current time window can be understood as a local analysis interval within a continuously sampled signal, reflecting the user's current short-term movement rhythm while ensuring real-time processing capabilities. Periodic features characterize the recurring pattern of the signal within this time window, such as period length, strength of periodic fluctuations, and signal repeatability. For example, when a user jogs at a relatively stable pace, the head micro-motion signals typically exhibit regular, repetitive fluctuations within the continuous time window, with corresponding periodic features being quite pronounced. However, when the user suddenly decelerates, stops, or turns their head sharply, the periodicity of the head micro-motion signals may weaken or even be disrupted, and the extracted periodic features will change accordingly.

[0018] In some optional implementations of this embodiment, the time periods corresponding to active head movements such as head turning, head nodding, or significant deviations from gait rhythm can also be identified based on the angular velocity data or attitude change rate in the inertial measurement data. When the time period is identified, the head micro-motion signal corresponding to the time period can be removed, or the participation weight of the signal corresponding to the time period in periodic feature extraction can be reduced, so as to reduce the interference of active head movements on the gait frequency extraction and periodic feature recognition results.

[0019] Step S103: Determine the step frequency and period stability of the current time window based on the periodic characteristics, and update the mapping parameters between the step frequency and the movement speed based on the GNSS velocity data when the GNSS quality data meets the calibration conditions.

[0020] In this embodiment, after obtaining the periodic features, the step frequency and periodic stability of the current time window are determined based on the periodic features. When the GNSS quality data meets the calibration conditions, the mapping parameter between step frequency and movement speed is updated based on the GNSS velocity data. Step frequency refers to the frequency of repetitive motion rhythms per unit time, typically related to the gait rhythm of a user's walking or running. Periodic stability characterizes whether the periodic features extracted within the current time window are continuous, clear, and reliable; essentially, it reflects whether the current head micro-motion signal is suitable for velocity estimation. The mapping parameter between step frequency and movement speed is the corresponding parameter used to convert the head micro-motion rhythm into actual movement speed. This parameter can be a proportionality coefficient, a functional relationship parameter, or other forms of velocity mapping basis. Because different users have differences in height, stride length, running posture, wearing method, and current movement state, a fixed step frequency cannot simply correspond to a fixed speed. Instead, when the GNSS quality is high, reliable GNSS velocity data is used to dynamically update the mapping parameter so that it continuously matches the user's actual movement state. The calibration conditions refer to GNSS quality data meeting preset requirements, indicating that the current GNSS velocity data has high reliability. Examples include a sufficient number of satellites, stable velocity changes, and low dispersion. Only when these conditions are met is GNSS velocity data used as the basis for updating mapping parameters, thus avoiding the erroneous introduction of abnormal GNSS velocities into the parameter modeling process. For example, even with the same step frequency of 160 steps per minute, different users' actual running speeds may differ. When GNSS quality is good, the system can update the mapping parameters based on the correspondence between the current step frequency and GNSS velocity, ensuring that speed can still be reasonably estimated based on step frequency even when the GNSS signal is unstable.

[0021] Step S104: Based on the GNSS quality data and the periodic stability, determine the velocity calculation status of the current time window as calibration status, continuation calculation status, or recovery status. When the velocity calculation state is in calibration state, the corrected velocity is determined based on the GNSS velocity data and the mapping parameters; when the velocity calculation state is in continuation state, the continuation velocity is determined based on the step frequency and the mapping parameters; when the velocity calculation state is in recovery state, the correction amount is determined based on the recovered GNSS velocity data, and the correction amount is allocated according to the periodic stability corresponding to each continuation time window before recovery, so as to perform retrospective correction on the continuation velocity corresponding to the continuation time window before recovery, and obtain the velocity after retrospective correction.

[0022] In this embodiment, the velocity calculation status of the current time window is determined as calibration, continuation, or recovery based on GNSS quality data and period stability. The purpose is to dynamically select a suitable velocity processing strategy based on the current signal conditions, rather than always using a single calculation method. The calibration state typically corresponds to a situation where GNSS quality is high and head micro-motion rhythm is relatively stable. At this time, the system can reliably utilize GNSS velocity data and simultaneously correct the mapping parameters between step frequency and movement speed, making it suitable for velocity calibration. The continuation state typically corresponds to a situation where GNSS quality deteriorates or does not meet calibration conditions, but period stability remains high. Although GNSS velocity data is no longer suitable as a direct basis, the step frequency rhythm reflected by head micro-motion can still be used in conjunction with the established mapping parameters for velocity continuation. The recovery state corresponds to the stage where GNSS quality returns from poor to meeting calibration conditions. At this time, the GNSS signal is reliable, and the system not only needs to reuse GNSS velocity data but also needs to correct any errors that may have accumulated in the previous continuation stage. For example, when a user is running on an open road, the system can be in calibration mode; when the user enters an area obstructed by tall buildings, the GNSS quality deteriorates but the gait rhythm remains relatively clear, and the system switches to recalculation mode; when the user returns to an open area, the GNSS quality recovers, and the system enters recovery mode to compensate for the recalculation results during the obstruction period.

[0023] After determining the velocity calculation state, the corresponding velocity results are determined according to different states. When the velocity calculation state is calibration, the corrected velocity is determined based on GNSS velocity data and mapping parameters. This corrected velocity is not a simple copy of the GNSS velocity, but rather, while using GNSS velocity as a reliable reference, it combines the current mapping parameters to ensure that the output velocity is consistent with the movement rhythm reflected by head micro-movements, thereby improving the stability and adaptability of the velocity output. When the velocity calculation state is continuation calculation, the continuation calculation velocity is determined based on the step frequency and mapping parameters. At this time, the system mainly uses the step frequency rhythm corresponding to the head micro-movement signal to continuously extrapolate the current velocity, thus avoiding velocity interruption during periods of GNSS quality degradation or short-term failure. The continuation calculation velocity can be understood as a substitute velocity result obtained based on the calibrated step frequency-velocity relationship when the current GNSS conditions are insufficient for direct velocity measurement. When the velocity calculation state is recovery, the correction amount is determined based on the recovered GNSS velocity data, and this correction amount is allocated according to the periodic stability corresponding to each continuation calculation time window before recovery. This is used to retrospectively correct the continuation calculation velocity corresponding to the continuation calculation time window before recovery, obtaining the retrospectively corrected velocity. The correction amount here refers to the error between the recovered reliable GNSS velocity and the previously calculated result. The so-called allocation of correction amount according to the periodic stability corresponding to each calculation time window means that instead of applying an average correction to all calculation time windows, the error is allocated differently based on the reliability of the head micro-movement rhythm within each time window. This allows for more targeted correction of time windows with lower periodic stability and higher error risk. For example, if a user runs along a tree-lined road with poor GNSS signal, and their running posture is relatively stable in the first half but fluctuates in rhythm in the second half due to avoiding pedestrians, then after GNSS recovery, the system can allocate more correction amount to the calculation result corresponding to the second half, making the overall velocity sequence closer to the actual movement process.

[0024] Step S105: Smooth the corrected speed, the calculated speed, or the backtracked corrected speed to obtain the output speed, and update the cumulative motion distance and the displayed speed according to the output speed.

[0025] In this embodiment, after obtaining the corrected speed, the continued calculation speed, or the speed after backtracking correction, the speed results are smoothed to obtain the output speed. The cumulative motion distance and the displayed speed are then updated based on the output speed. The smoothing process reduces instantaneous fluctuations in speed values ​​within a local time window, making the final output result more continuous and stable while maintaining real-time responsiveness, thus avoiding abrupt changes during direct display or accumulation. The output speed is the final speed result used for motion statistics and interface presentation. The cumulative motion distance is obtained by gradually accumulating the output speed over time, reflecting the total distance traveled by the user since the start of the motion. The displayed speed is the speed value presented to the user in real-time on the head-mounted device interface. Since users are sensitive to the continuity and stability of values ​​in head-mounted display scenarios, uniformly smoothing the speed results obtained under different states can significantly improve the display experience and enhance the reliability of distance statistics. For example, when users check the glasses display while running, they expect to see a speed value that matches their physical sensation and changes smoothly, rather than a speed that fluctuates due to GNSS jitter; after the exercise, the cumulative distance calculated by the system should also be as close as possible to the actual running distance.

[0026] This application incorporates head micro-motion signals and GNSS quality data simultaneously to perform segmented fusion processing on velocity calculation during motion. This enables the system to not only calibrate motion speed using GNSS velocity data when GNSS quality is good, but also to continue calculating speed based on the motion rhythm reflected by head micro-motions when GNSS quality fluctuates or fails briefly. After GNSS is restored, the continued calculation results are retrospectively corrected. This achieves continuous, accurate, and stable output of motion speed in complex motion scenarios, further improving the reliability of cumulative motion distance calculation and display results, and enhancing the actual user experience of head-mounted devices in motion monitoring scenarios.

[0027] In some optional implementations of this embodiment, the steps of performing attitude alignment and filtering on the inertial measurement data to obtain head micro-motion signals include: The head posture is determined based on the inertial measurement data, and the acceleration data is converted to a gravity-aligned coordinate system; The vertical and lateral periodic components are extracted from the converted acceleration data, and bandpass filtering is performed on the vertical and lateral periodic components to obtain the head micro-motion signal.

[0028] In this embodiment, during actual wear, the sensor's installation orientation is often not entirely consistent with the actual direction of human movement. For example, different users may slightly tilt forward, backward, or turn left or right when wearing glasses. Therefore, directly using raw acceleration data is difficult to accurately reflect the true dynamic characteristics of the head during user movement. To address this, in this embodiment, the head posture is first determined based on inertial measurement data. The head posture refers to the directional state of the head-mounted device relative to a reference spatial coordinate system, which can be estimated by sensing the direction of gravity with an accelerometer and combining it with changes in angular velocity measured by a gyroscope. After obtaining the head posture, the acceleration data is converted to a gravity-aligned coordinate system, making the converted data use the direction of gravity as a unified reference. The gravity-aligned coordinate system can be understood as a coordinate system where the longitudinal axis is aligned with or relatively fixed to the direction of gravity, thus eliminating the influence of wearing posture differences on subsequent analysis. Furthermore, vertical and lateral periodic components are extracted from the converted acceleration data. The vertical periodic component mainly reflects the up-and-down undulations of the head during walking or running, while the lateral periodic component mainly reflects the left-and-right periodic changes of the head as the body swings. Since the original signal may also contain random jitters, sudden impacts, and slow head swings unrelated to gait, bandpass filtering is applied to these two components to preserve the periodic changes within the target motion frequency band and suppress out-of-band noise, ultimately obtaining a head micro-motion signal that can stably characterize the motion rhythm. For example, when a user wears smart sports glasses and jogs, their head will produce continuous and minute up-and-down and left-and-right swings with each step. After posture alignment, relatively regular periodic fluctuations can be separated from the acceleration signal. After bandpass filtering, a head micro-motion signal corresponding to the running rhythm is obtained, providing reliable input for subsequent periodic feature extraction.

[0029] This application effectively reduces the impact of head-mounted device wearing angle differences and head posture changes on motion feature extraction by performing attitude alignment processing on inertial measurement data and converting acceleration data to a gravity-aligned coordinate system. At the same time, by extracting vertical and lateral periodic components and performing bandpass filtering, effective periodic components related to gait rhythm can be separated from the original inertial measurement data, suppressing random noise, sudden interference, and low-frequency swaying components unrelated to motion rhythm, thereby obtaining a more stable and clear head micro-motion signal, providing a reliable data foundation for subsequent gait frequency extraction and velocity estimation.

[0030] In some optional implementations of this embodiment, the step of extracting the periodic features of the current time window based on the head micro-motion signal includes: The head micro-motion signal is processed by sliding windowing, and peak detection and autocorrelation analysis are performed on the signal in each current time window to obtain the main period and period amplitude. The period stability is determined based on the change in the main period and the change in the period amplitude between adjacent current time windows, and the step frequency is determined based on the main period.

[0031] In this embodiment, the head micro-motion signal is not analyzed all at once during the entire movement process. Instead, it is processed by sliding windows of a preset length. That is, multiple local analysis intervals are sequentially extracted from the continuously sampled time series as the current time window, and each current time window corresponds to a short-term movement state. In this way, real-time performance can be ensured while tracking the dynamic changes in the user's movement rhythm. For the signal within each current time window, peak detection and autocorrelation analysis are performed. Peak detection is used to identify local maxima or minima of the signal within a time window to reflect recurring peaks or troughs in the movement cycle. Autocorrelation analysis is used to measure the similarity between the signal and itself at different time delays, thereby identifying the main recurring cycle in the signal. Based on this analysis, the main cycle and cycle amplitude can be obtained. The main cycle refers to the dominant recurrence time interval within the current time window, reflecting the basic cycle of the current movement rhythm; the cycle amplitude characterizes the strength of the cycle fluctuation and can reflect the significance of head micro-movements. Furthermore, the periodic stability is determined based on the changes in the principal period and the period amplitude between adjacent current time windows. The smaller the change in the principal period and the smoother the change in the period amplitude, the more continuous and stable the movement rhythm within adjacent time windows, resulting in higher periodic stability. Conversely, if the principal period and period amplitude fluctuate significantly, it indicates that the current head micro-movement rhythm is unstable, and the periodic stability decreases accordingly. The step frequency can also be determined based on the principal period, typically obtained through the conversion relationship between the principal period and unit time. For example, when a user runs at a relatively constant speed, the head micro-movement signals within multiple adjacent time windows often exhibit approximately repetitive rhythms. In this case, the principal period remains relatively stable, the period amplitude changes little, and the corresponding periodic stability is high. However, when the user suddenly stops, turns their head, or takes a step to avoid an obstacle, the principal period and amplitude between time windows may change significantly, leading to a decrease in periodic stability. Based on this, the system's ability to identify the current rhythm becomes less reliable.

[0032] In some optional implementations, for the time period identified as active head movement, the interference weight can be determined based on the angular velocity amplitude, attitude change rate, or duration of the corresponding time period. The interference weight is then used to weight and correct the main period change and the period amplitude change to obtain the period stability after anti-interference processing. The period stability after anti-interference processing can be further used to determine the subsequent velocity calculation state to improve the robustness of the head-mounted device in step frequency extraction and state recognition under head turning, head nodding, or road bumpy scenarios.

[0033] This application uses sliding windowing to process head micro-motion signals and combines peak detection and autocorrelation analysis to obtain the main period and period amplitude. This allows for the accurate extraction of periodic features in the user's current short-term motion state while ensuring real-time performance. Furthermore, by determining the period stability based on the changes in the main period and period amplitude between adjacent time windows, not only can step frequency information be obtained, but the reliability of the current motion rhythm can also be quantitatively evaluated. This provides a basis for subsequent speed calculation and state determination, improving the pertinence and stability of speed estimation under complex motion state changes.

[0034] In some optional implementations of this embodiment, the step of determining the velocity calculation state of the current time window as a calibration state, a continuation calculation state, or a recovery state based on the GNSS quality data and the periodic stability includes: The number of satellites, velocity jump variable, and velocity dispersion corresponding to the current time window are extracted as the GNSS quality data. When the GNSS quality data meets the calibration conditions and the period stability is greater than the preset stability threshold, the velocity calculation state is determined to be the calibration state. When the GNSS quality data does not meet the calibration conditions and the period stability is greater than the preset stability threshold, the velocity calculation state is determined to be a continuation calculation state. When the GNSS quality data changes from not meeting the calibration conditions to meeting the calibration conditions, the velocity calculation state is determined to be in a recovery state.

[0035] In this embodiment, GNSS quality data is not limited to a single parameter, but rather a set of evaluation information comprehensively reflecting the reliability of the current GNSS velocity data. In this embodiment, the number of satellites, velocity jump variable, and velocity dispersion corresponding to the current time window are extracted as GNSS quality data. The number of satellites characterizes the current satellite resources available for positioning and velocity measurement; generally, the more satellites available, the higher the reliability of GNSS velocity measurement. The velocity jump variable characterizes the degree of abrupt change in GNSS velocity values ​​between adjacent sampling times; if the velocity jump variable is too large, it may indicate an abnormal jump in GNSS velocity. The velocity dispersion characterizes the degree of fluctuation and dispersion of the GNSS velocity sequence within the current time window; if the dispersion is high, it indicates that the GNSS velocity within that time window is unstable. Based on the above GNSS quality data and the obtained periodic stability, the state of the current time window is determined. When GNSS quality data meets calibration conditions and period stability is greater than the preset stability threshold, it indicates that the GNSS velocity measurement result is relatively reliable, and the head micro-movement rhythm is also relatively stable. This is suitable for updating mapping parameters using GNSS velocity data, and the velocity calculation state is thus determined to be in calibration mode. When GNSS quality data does not meet calibration conditions but period stability is still greater than the preset stability threshold, it indicates that the GNSS velocity data is not suitable for direct velocity measurement, but the head micro-movement rhythm can still be used as a basis for velocity estimation. In this case, the velocity calculation state is determined to be in continuation mode. When GNSS quality data changes from not meeting calibration conditions to meeting them, it indicates that the GNSS signal has undergone a process from poor to reliable. In this case, the velocity calculation state is determined to be in recovery mode to compensate and correct the velocity results from the previous continuation stage. For example, when a user wearing a head-mounted device runs on a tree-lined path, the number of satellites decreases and GNSS velocity fluctuations increase after entering a densely wooded area, but the running rhythm remains clear. In this case, the system can determine it to be in continuation mode. When the user runs out of the obstructed area, the number of satellites increases and the velocity fluctuation decreases, thus entering recovery mode, creating conditions for subsequent backtracking correction.

[0036] In some optional implementations of this embodiment, when the GNSS quality data does not meet the calibration conditions and the period stability is not greater than the preset stability threshold, the update of the mapping parameters can be paused, and the output speed corresponding to the previous time window can be maintained, or the output speed corresponding to the previous time window can be updated according to the preset attenuation strategy as the conservative output speed for the current time window; after the period stability recovers to above the preset stability threshold, or after the GNSS quality data meets the calibration conditions again, the corresponding continuation state, calibration state, or recovery state can be entered.

[0037] This application uses the number of satellites, velocity jump variables, and velocity dispersion corresponding to the current time window as GNSS quality data, and combines this with periodic stability to determine the velocity calculation status. This enables a more comprehensive identification of the current signal conditions and avoids misjudgments caused by relying solely on a single GNSS index or a single inertial rhythm index. Furthermore, by dividing the velocity calculation status into calibration status, continuation status, and recovery status, the system can adaptively select appropriate processing strategies based on GNSS quality changes and motion rhythm stability. This enhances the motion monitoring scheme's adaptability to GNSS fluctuations, short-term loss of lock, and recovery processes, and improves the continuity and robustness of the overall velocity calculation process.

[0038] In some optional implementations of this embodiment, when the velocity calculation state is a calibration state, determining the corrected velocity based on the GNSS velocity data and the mapping parameters includes: Calculate the current mapping parameters based on the correspondence between the GNSS velocity data and the step frequency corresponding to the current time window; The current mapping parameters are weighted and fused with the historical mapping parameters to obtain the updated mapping parameters; The correction speed is determined based on the updated mapping parameters.

[0039] In this embodiment, when the system determines that the current time window is in calibration mode, it indicates that the GNSS quality is good, the GNSS velocity data can be used as a relatively reliable reference, and the step frequency information corresponding to the head micro-motion signal also has high reliability. Therefore, the current mapping parameters can be calculated using the correspondence between the GNSS velocity data and step frequency corresponding to the current time window. The mapping parameters here can be understood as the correlation coefficient, proportional relationship, or functional relationship between step frequency and actual movement speed, used to convert the step frequency derived from head micro-motion into a velocity value that more closely approximates the actual ground movement state. Since the relationship between step frequency and speed may change for the same user at different movement stages, different slopes, or different fatigue states, relying solely on a fixed parameter set once is insufficient to adapt to the actual movement process in the long term. To improve adaptability, this embodiment performs weighted fusion of the current mapping parameters and historical mapping parameters to obtain updated mapping parameters. Weighted fusion can be understood as a comprehensive balancing process of historical experience values ​​and current observation values ​​to avoid drastic changes in mapping parameters due to accidental fluctuations within a single time window. The corrected speed is determined based on the updated mapping parameters, ensuring that the current output speed retains the authenticity of the GNSS speed data while also maintaining consistency with the rhythm of head micro-movements. For example, as a user starts running, their stride frequency gradually increases, and the GNSS speed also increases synchronously. The system can calculate the current mapping parameters based on the relationship between the current stride frequency and GNSS speed, and merge them with historical mapping parameters formed during previous lower speed phases. This allows for a gradual adjustment to a mapping relationship that better reflects the current running state, resulting in a more stable corrected speed that more closely resembles the actual movement state.

[0040] This application calculates the current mapping parameters based on the correspondence between GNSS velocity data and step frequency in the current time window under calibration conditions, and then weights and fuses the current mapping parameters with historical mapping parameters. This enables the mapping relationship between step frequency and movement speed to be dynamically adjusted according to the current user state and movement process, rather than remaining fixed, thereby improving the adaptability of the mapping parameters to individual differences and changes in movement state. Based on this, the corrected speed is determined according to the updated mapping parameters, which helps to maintain the accuracy of the speed results while ensuring output stability, providing a more accurate parameter basis for speed estimation in subsequent calculation states.

[0041] In some optional implementations of this embodiment, determining the continuous calculation speed based on the step frequency and the mapping parameters when the speed calculation state is a continuous calculation state includes: Calculate the candidate velocity based on the step frequency and mapping parameters corresponding to the current time window; Based on the output speed corresponding to the previous time window and the preset speed change threshold, the candidate speed is subjected to a continuity constraint to obtain the continued calculation speed. The cumulative distance traveled is updated based on the calculated speed.

[0042] In this embodiment, when the system determines that the current time window is in a continuous calculation state, it indicates that the GNSS quality data no longer meets the calibration conditions, and the current GNSS velocity data is not suitable as a direct basis for velocity output. However, the periodic stability is still high, indicating that the user's movement rhythm is clear and the head micro-motion signal has high reliability. Therefore, candidate velocities can be calculated based on the step frequency and mapping parameters corresponding to the current time window. Here, candidate velocity refers to the initial velocity estimate obtained based on the current step frequency and the existing mapping relationship. This velocity value can continuously estimate the user's movement velocity during short-term GNSS failures or fluctuations. Considering that candidate velocities may still be affected by local rhythm fluctuations, in order to prevent unreasonable sudden changes in output velocity, this embodiment further imposes continuity constraints on candidate velocities based on the output velocity corresponding to the previous time window and a preset velocity change threshold. The so-called continuity constraint refers to limiting the amplitude of velocity changes between adjacent time windows, so that the velocity result obtained in the current time window maintains a reasonable connection with the output velocity of the previous time window, thereby suppressing instantaneous jumps caused by local signal disturbances. The result after continuity constraints is the calculated speed. The accumulated distance is then updated based on this speed, ensuring continuous distance tracking even during periods of degraded GNSS quality. For example, if a user briefly enters a tunnel or under an overpass while running, the GNSS speed measurement may fluctuate significantly, but their running rhythm remains relatively stable. In this case, the system can obtain candidate speeds based on the current stride frequency and mapping parameters. Combined with the continuity requirement of the speed output from the previous time window, a relatively stable calculated speed is formed, and the distance traveled during this phase continues to accumulate, preventing display interruptions or abrupt changes in distance statistics.

[0043] This application calculates candidate velocities based on the step frequency and mapping parameters corresponding to the current time window during continuous calculation, and combines the output velocity corresponding to the previous time window and the preset velocity change threshold to constrain the candidate velocities. This allows for a relatively stable continuous calculation velocity even during periods of GNSS quality degradation or short-term failure, avoiding speed display interruptions or abnormal jumps. At the same time, updating the cumulative motion distance based on the continuous calculation speed ensures that motion distance statistics continue during GNSS anomaly phases, thereby improving the integrity and usability of motion monitoring results in complex environments.

[0044] In some optional implementations of this embodiment, when the velocity calculation state is in a recovery state, the correction amount is determined based on the recovered GNSS velocity data, and the correction amount is allocated according to the periodic stability corresponding to each continuation time window before recovery, so as to perform retrospective correction on the continuation velocity corresponding to the continuation time window before recovery, including: The correction amount is determined based on the calculation speed corresponding to the calculation time window before the recovery of the GNSS velocity data; The periodic stability corresponding to each continuation time window before recovery is normalized, and the correction amount is allocated according to the normalized periodic stability to correct the continuation speed and cumulative movement distance corresponding to each continuation time window. The speed after backtracking correction is smoothed to obtain the output speed, and the display speed is updated according to the output speed.

[0045] In this embodiment, when the GNSS quality recovers from failing to meet calibration conditions to meeting them, the system does not simply switch back to the current GNSS velocity as the output. Instead, it needs to compensate for any errors that may have accumulated during the previous continuation calculation phase. To this end, a correction amount is first determined based on the recovered GNSS velocity data and the calculation velocity corresponding to the previous continuation calculation time window. This correction amount can be understood as the deviation between the calculation result and the recovered reliable GNSS reference, used to characterize the overall error level present in the previous continuation calculation phase. Further, the periodic stability corresponding to each continuation calculation time window before recovery is normalized, that is, the periodic stability of each time window is converted into a comparable and assignable weighted form, so that the stability magnitude corresponding to each time window can participate in error allocation on a unified scale. Subsequently, a correction amount is allocated based on the normalized periodic stability to correct the calculation velocity and cumulative movement distance corresponding to each continuation calculation time window. The significance of this approach lies in the fact that the reliability of head micro-movement rhythms may differ within different continuation time windows. If the periodic stability is high within a certain time window, it indicates that the continuation data within that window is more reliable, and corresponding corrections can be smaller or more cautious. Conversely, if the periodic stability is low within a certain time window, it indicates that the window is more affected by abnormal movements or rhythmic fluctuations, and correspondingly, more significant corrections can be made. This backtracking correction method, based on stability allocation, allows for more detailed velocity trajectory correction throughout the continuation phase, rather than the distortion caused by uniform average correction. Finally, the velocity after backtracking correction is smoothed to obtain the output velocity, and the display velocity is updated based on the output velocity, thus ensuring that the interface display does not exhibit significant jumps due to correction actions after GNSS recovery. For example, if a user's running posture is relatively stable in the first half of the GNSS run but becomes disordered in the second half due to avoiding pedestrians, the system can make more significant corrections to the second half of the GNSS run after GNSS recovery, based on the stability differences of each calculation time window, while maintaining relatively small corrections to the first half. This ultimately makes the speed display after recovery more consistent with the entire movement process, and the distance statistics results closer to the true value.

[0046] This application determines the correction amount based on the recovered GNSS velocity data and the calculation velocity corresponding to the previous calculation time window in the recovered state. After normalizing the periodic stability corresponding to each calculation time window, the correction amount is allocated. This allows for differentiated retrospective correction of calculation errors based on the reliability of motion rhythms within different calculation time windows, rather than using a uniform average correction method. This makes the recovered velocity sequence and cumulative motion distance closer to the actual motion situation. Furthermore, smoothing the retrospectively corrected velocity and updating the displayed velocity helps reduce abrupt changes in the interface display after GNSS recovery, improving the display stability and user perception continuity of the head-mounted device during motion monitoring.

[0047] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing related hardware through computer-readable instructions. These computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, optical disk, or read-only memory (ROM), or random access memory (RAM).

[0048] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0049] Further reference Figure 2 As a response to the above Figure 1 To implement the method shown, this application provides an embodiment of a motion monitoring system based on the fusion of head micro-motion and GNSS quality segmentation. This system embodiment is similar to... Figure 1 Corresponding to the method embodiments shown, the system can be specifically applied to various electronic devices.

[0050] like Figure 2 As shown, the motion monitoring system 200 based on head micro-motion and GNSS quality segmentation fusion described in this embodiment includes: an acquisition module 201, an identification module 202, a calculation module 203, a training module 204, and a processing module 205. Wherein: The acquisition module 201 is used to acquire inertial measurement data and GNSS data of the head-mounted device during the movement process, wherein the GNSS data includes at least GNSS velocity data and GNSS mass data; The extraction module 202 is used to perform attitude alignment and filtering on the inertial measurement data to obtain head micro-motion signals, and extract the periodic features of the current time window based on the head micro-motion signals; The first update module 203 is used to determine the step frequency and periodic stability of the current time window based on the periodic characteristics, and update the mapping parameters between the step frequency and the movement speed based on the GNSS velocity data when the GNSS quality data meets the calibration conditions. The determination module 204 is used to determine the velocity calculation status of the current time window as a calibration state, a continuation state, or a recovery state based on the GNSS quality data and the periodic stability. When the velocity calculation state is in calibration state, the corrected velocity is determined based on the GNSS velocity data and the mapping parameters; when the velocity calculation state is in continuation state, the continuation velocity is determined based on the step frequency and the mapping parameters; when the velocity calculation state is in recovery state, the correction amount is determined based on the recovered GNSS velocity data, and the correction amount is allocated according to the periodic stability corresponding to each continuation time window before recovery, so as to perform retrospective correction on the continuation velocity corresponding to the continuation time window before recovery, and obtain the velocity after retrospective correction. The second update module 205 is used to smooth the corrected speed, the continued calculation speed, or the backtracked corrected speed to obtain the output speed, and update the cumulative motion distance and the displayed speed according to the output speed.

[0051] The motion monitoring system based on head micro-motion and GNSS quality segment fusion provided in this embodiment of the invention can realize all the processes of the motion monitoring method based on head micro-motion and GNSS quality segment fusion in the above embodiments. The functions and technical effects of each module in the device are the same as those of the motion monitoring method based on head micro-motion and GNSS quality segment fusion in the above embodiments, and will not be repeated here.

[0052] To address the aforementioned technical problems, embodiments of this application also provide a computer device. Please refer to [link / reference needed]. Figure 3 , Figure 3 This is a basic structural block diagram of the computer device in this embodiment.

[0053] The computer device 3 includes a memory 31, a processor 32, and a network interface 33 that are interconnected via a system bus. It should be noted that only the computer device 3 with components 31-33 is shown in the figure; however, it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. Those skilled in the art will understand that the computer device described here is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0054] The computer device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device can interact with the user via a keyboard, mouse, remote control, touchpad, or voice control.

[0055] The memory 31 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 31 may be an internal storage unit of the computer device 3, such as the hard disk or memory of the computer device 3. In other embodiments, the memory 31 may also be an external storage device of the computer device 3, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 3. Of course, the memory 31 may also include both the internal storage unit and its external storage device of the computer device 3. In this embodiment, the memory 31 is typically used to store the operating system and various application software installed on the computer device 3, such as computer-readable instructions for a motion monitoring method based on head micro-motion and GNSS quality segmentation fusion. In addition, the memory 31 can also be used to temporarily store various types of data that have been output or will be output.

[0056] In some embodiments, the processor 32 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. The processor 32 is typically used to control the overall operation of the computer device 3. In this embodiment, the processor 32 is used to execute computer-readable instructions stored in the memory 31 or to process data, for example, to execute computer-readable instructions for the motion monitoring method based on head micro-motion and GNSS quality segmentation fusion.

[0057] The network interface 33 may include a wireless network interface or a wired network interface, which is typically used to establish communication connections between the computer device 3 and other electronic devices.

[0058] This application also provides another embodiment, namely, providing a computer-readable storage medium storing computer-readable instructions that can be executed by at least one processor to cause the at least one processor to perform the steps of the motion monitoring method based on head micro-motion and GNSS quality segment fusion as described above.

[0059] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0060] The above are merely preferred embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A motion monitoring method based on the fusion of head micro-motion and GNSS quality segmentation, characterized in that, Includes the following steps: Acquire inertial measurement data and GNSS data of the head-mounted device during movement, wherein the GNSS data includes at least GNSS velocity data and GNSS quality data; The inertial measurement data is aligned and filtered to obtain head micro-motion signals, and the periodic features of the current time window are extracted based on the head micro-motion signals. The step frequency and periodic stability of the current time window are determined based on the periodic characteristics, and the mapping parameters between the step frequency and the movement speed are updated based on the GNSS velocity data when the GNSS quality data meets the calibration conditions. Based on the GNSS quality data and the periodic stability, the velocity calculation status of the current time window is determined as calibration status, continuation calculation status, or recovery status. When the velocity calculation state is in calibration state, the corrected velocity is determined based on the GNSS velocity data and the mapping parameters; when the velocity calculation state is in continuation state, the continuation velocity is determined based on the step frequency and the mapping parameters; when the velocity calculation state is in recovery state, the correction amount is determined based on the recovered GNSS velocity data, and the correction amount is allocated according to the periodic stability corresponding to each continuation time window before recovery, so as to perform retrospective correction on the continuation velocity corresponding to the continuation time window before recovery, and obtain the velocity after retrospective correction. The corrected speed, the continued calculation speed, or the backtracked corrected speed are smoothed to obtain the output speed, and the cumulative motion distance and the displayed speed are updated according to the output speed.

2. The method according to claim 1, characterized in that, The steps of performing attitude alignment and filtering on the inertial measurement data to obtain head micro-motion signals include: The head posture is determined based on the inertial measurement data, and the acceleration data is converted to a gravity-aligned coordinate system; The vertical and lateral periodic components are extracted from the converted acceleration data, and bandpass filtering is performed on the vertical and lateral periodic components to obtain the head micro-motion signal.

3. The method according to claim 2, characterized in that, The steps for extracting the periodic features of the current time window based on the head micro-motion signals include: The head micro-motion signal is processed by sliding windowing, and peak detection and autocorrelation analysis are performed on the signal in each current time window to obtain the main period and period amplitude. The period stability is determined based on the change in the main period and the change in the period amplitude between adjacent current time windows, and the step frequency is determined based on the main period.

4. The method according to claim 1, characterized in that, The step of determining the velocity calculation status of the current time window as a calibration state, a continuation state, or a recovery state based on the GNSS quality data and the periodic stability includes: The number of satellites, velocity jump variable, and velocity dispersion corresponding to the current time window are extracted as the GNSS quality data. When the GNSS quality data meets the calibration conditions and the period stability is greater than the preset stability threshold, the velocity calculation state is determined to be the calibration state. When the GNSS quality data does not meet the calibration conditions and the period stability is greater than the preset stability threshold, the velocity calculation state is determined to be a continuation calculation state. When the GNSS quality data changes from not meeting the calibration conditions to meeting the calibration conditions, the velocity calculation state is determined to be in a recovery state.

5. The method according to claim 1, characterized in that, When the velocity calculation state is in calibration state, the corrected velocity is determined based on the GNSS velocity data and the mapping parameters, including: Calculate the current mapping parameters based on the correspondence between the GNSS velocity data and the step frequency corresponding to the current time window; The current mapping parameters are weighted and fused with the historical mapping parameters to obtain the updated mapping parameters; The correction speed is determined based on the updated mapping parameters.

6. The method according to claim 1, characterized in that, When the speed calculation state is in the continuation calculation state, the continuation calculation speed is determined according to the step frequency and the mapping parameters, including: Calculate the candidate velocity based on the step frequency and mapping parameters corresponding to the current time window; Based on the output speed corresponding to the previous time window and the preset speed change threshold, the candidate speed is subjected to a continuity constraint to obtain the continued calculation speed. The cumulative distance traveled is updated based on the calculated speed.

7. The method according to claim 1, characterized in that, When the velocity calculation state is in the recovery state, a correction amount is determined based on the recovered GNSS velocity data, and the correction amount is allocated according to the periodic stability corresponding to each continuation time window before recovery, so as to perform retrospective correction on the continuation velocity corresponding to the continuation time window before recovery, including: The correction amount is determined based on the calculation speed corresponding to the calculation time window before the recovery of the GNSS velocity data; The periodic stability corresponding to each continuation time window before recovery is normalized, and the correction amount is allocated according to the normalized periodic stability to correct the continuation speed and cumulative movement distance corresponding to each continuation time window. The speed after backtracking correction is smoothed to obtain the output speed, and the display speed is updated according to the output speed.

8. A motion monitoring system based on the fusion of head micro-motion and GNSS quality segmentation, characterized in that, include: The acquisition module is used to acquire inertial measurement data and GNSS data of the head-mounted device during the movement process, wherein the GNSS data includes at least GNSS velocity data and GNSS quality data; The extraction module is used to perform attitude alignment and filtering on the inertial measurement data to obtain head micro-motion signals, and extract the periodic features of the current time window based on the head micro-motion signals. The first update module is used to determine the step frequency and periodic stability of the current time window based on the periodic characteristics, and update the mapping parameters between the step frequency and the movement speed based on the GNSS velocity data when the GNSS quality data meets the calibration conditions. The determination module is used to determine the velocity calculation status of the current time window as calibration status, continuation calculation status or recovery status based on the GNSS quality data and the periodic stability. When the velocity calculation state is in calibration state, the corrected velocity is determined based on the GNSS velocity data and the mapping parameters; when the velocity calculation state is in continuation state, the continuation velocity is determined based on the step frequency and the mapping parameters; when the velocity calculation state is in recovery state, the correction amount is determined based on the recovered GNSS velocity data, and the correction amount is allocated according to the periodic stability corresponding to each continuation time window before recovery, so as to perform retrospective correction on the continuation velocity corresponding to the continuation time window before recovery, and obtain the velocity after retrospective correction. The second update module is used to smooth the corrected speed, the continued calculation speed, or the backtracked corrected speed to obtain the output speed, and update the cumulative motion distance and the displayed speed according to the output speed.

9. A computer device, characterized in that, The device includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor executes the computer-readable instructions to implement the steps of the motion monitoring method based on head micro-motion and GNSS quality segment fusion as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the motion monitoring method based on head micro-motion and GNSS quality segment fusion as described in any one of claims 1 to 7.

Images