Gait analysis system and gait analysis method

Abstract

This application discloses a gait analysis system and method. The gait analysis system includes multiple inertial measurement modules, multiple pressure measurement modules, a depth camera, an optical motion capture module, a data filtering module, and a main control module. Through the cooperation of multiple modules, various types of data reflecting gait characteristics are collected. The data can compensate for each other and collaboratively reflect the user's gait characteristics. Finally, the main control module obtains the user's gait analysis results, realizing a comprehensive analysis of gait characteristics such as stride length, stride width, stride frequency, gait rhythm, gait periodicity, gait stability, and gait coordination. This gait analysis system can eliminate the problem of inaccurate gait analysis caused by the limited information collected by a single sensor, reduce the error interference of external environmental influences on gait analysis, improve detection accuracy and reliability, and achieve accurate and comprehensive analysis of the user's gait.

Description

Technical Field

[0001] This application relates to the field of human gait analysis technology, and in particular to a gait analysis system and gait analysis method. Background Technology

[0002] Gait analysis measures and evaluates the movement patterns, biomechanical characteristics, and physiological performance of the human body during walking. It has wide applications in medicine, sports training, rehabilitation therapy, and biometrics.

[0003] In related technologies, using plantar pressure sensors to collect plantar pressure signals often requires placing multiple sensors at key locations on the sole of the foot to effectively reflect plantar pressure and then perform gait analysis.

[0004] However, the detection of plantar pressure is greatly affected by the number of sensors, their fixed positions and methods. A single sensor can collect a small amount of information and has low detection accuracy, and is easily affected by the external environment, resulting in large errors. Summary of the Invention

[0005] In view of this, this application provides a gait analysis system and gait analysis method, which can eliminate the problem of inaccurate gait analysis caused by the limited amount of information that a single sensor can collect, reduce the error interference of external environmental influences on gait analysis, improve detection accuracy and reliability, and achieve accurate and comprehensive analysis of the user's gait.

[0006] Specifically, the following technical solutions are included:

[0007] In a first aspect, embodiments of this application provide a gait analysis system, the gait analysis system comprising:

[0008] Multiple inertial measurement modules are used to detect acceleration and angular velocity data at the center of the user's torso, the outer sides of both knees, and the outer sides of both ankles;

[0009] Multiple pressure measurement modules are used to detect pressure data on the user's soles;

[0010] Infrared depth camera, used to detect depth image data of user movement;

[0011] An optical motion capture module is used to collect the user's three-dimensional position data;

[0012] The data filtering module is used to perform bandpass filtering on the acceleration data and the angular velocity data to obtain first filtered data, low-pass filtering on the pressure data to obtain second filtered data, and weighted average filtering on the depth image data to obtain third filtered data.

[0013] The main control module is used to determine the user's gait analysis results based on the first filtered data, the second filtered data, the third filtered data, and the three-dimensional position data. The gait analysis results include stride length, stride width, stride frequency, gait rhythm, gait periodicity, gait stability, and gait coordination.

[0014] In some embodiments, the optical motion capture module includes multiple optical motion capture cameras positioned around the user, multiple reflective markers positioned at joint points on the user's lower body, a POE+ switch, and a calibration rod.

[0015] In some embodiments, the main control module includes a feature extraction unit, which includes a first feature extraction subunit, a second feature extraction subunit, a third feature extraction subunit, and a fourth feature extraction subunit.

[0016] The first feature extraction subunit is used to determine the motion features of the user's torso and the forward, backward, left, and right tilt features of the torso based on the first filtered data.

[0017] The second feature extraction subunit is used to determine the pressure distribution, pressure changes, and pressure dynamic characteristics of the user's sole based on the second filtered data;

[0018] The third feature extraction subunit is used to determine the motion trajectory of the joints based on the third filtered data;

[0019] The fourth feature extraction subunit is used to determine the tracking position and motion trajectory of the marker point based on the three-dimensional position data.

[0020] In some embodiments, the main control module includes a multimodal data fusion unit, which includes a first data fusion unit and a second data fusion unit;

[0021] The first data fusion unit is used to fuse the motion characteristics of the user's torso, the forward, backward, left and right tilt characteristics of the torso, the pressure distribution of the user's soles, the pressure changes, and the pressure dynamic characteristics to obtain the first fused data.

[0022] The second data fusion unit is used to fuse the joint motion trajectory, the marker tracking position, and the marker motion trajectory to obtain second fused data.

[0023] In some embodiments, the main control module includes a gait analysis unit and a motion performance evaluation unit;

[0024] The gait analysis unit is used to determine stride length, stride width, stride frequency, gait rhythm, and gait periodicity based on the first fused data, and to determine gait stability and gait coordination based on the second fused data.

[0025] The sports performance evaluation unit is used to generate a sports performance evaluation report based on stride length, stride frequency, gait rhythm, gait periodicity, gait stability, and gait coordination. The sports performance evaluation report includes a visualization of stride length, stride length, stride frequency, gait rhythm, gait periodicity, gait stability, and gait coordination, as well as sports advantages and gait improvement suggestions.

[0026] In some embodiments, the main control module further includes an anomaly detection and analysis unit, which is used for:

[0027] Based on the user's torso movement characteristics, the torso's forward, backward, left, and right tilt characteristics, the user's foot pressure distribution, pressure changes, pressure dynamic characteristics, joint movement trajectories, and three-dimensional position data, abnormal features and abnormal locations are determined. The abnormal features include gait asymmetry, excessive stride length, excessive stride length, and gait instability.

[0028] Based on the abnormal features, a gait abnormality report is generated, which includes the abnormal features, the abnormal location, and gait improvement suggestions.

[0029] In some embodiments, the calibration rod includes an L-shaped calibration rod and a T-shaped calibration rod, used to calibrate multiple optical motion capture cameras so that the multiple optical motion capture cameras work synchronously.

[0030] In some embodiments, the main control module further includes a compensation and correction unit, the correction unit being specifically used for:

[0031] Eliminate data drift in the inertial measurement module and perform error compensation and correction on the inertial measurement module based on the three-dimensional position data;

[0032] Based on the three-dimensional position data, the sensitivity and response time of the pressure measurement module are corrected, and the phase of the pressure measurement module is adjusted based on the gait cycle data in the three-dimensional position data.

[0033] The depth image parameters of the infrared depth camera are calibrated, and the accuracy of the depth image data is adjusted based on the three-dimensional position data.

[0034] In some embodiments, the main control module further includes a data integration unit and a data segmentation unit;

[0035] The data integration unit is used to integrate the acceleration data, the angular velocity data, the pressure data, the depth image data, and the three-dimensional position data;

[0036] The data segmentation unit is used to segment the integrated acceleration data, angular velocity data, pressure data, depth image data, and three-dimensional position data. The segmentation process involves segmenting the integrated acceleration data, angular velocity data, pressure data, depth image data, and three-dimensional position data once at every threshold time interval to obtain segmented data.

[0037] Secondly, embodiments of this application provide a gait analysis method, the gait analysis method comprising:

[0038] Multiple inertial measurement modules detect acceleration and angular velocity data at the center of the user's torso, the outer sides of both knees, and the outer sides of both ankles;

[0039] Multiple pressure measurement modules detect pressure data on the user's soles;

[0040] Infrared depth cameras detect depth image data of user movement;

[0041] The optical motion capture module collects the user's three-dimensional position data;

[0042] The data filtering module performs bandpass filtering on the acceleration data and the angular velocity data to obtain first filtered data, performs low-pass filtering on the pressure data to obtain second filtered data, and performs weighted average filtering on the depth image data to obtain third filtered data.

[0043] The main control module determines the user's gait analysis results based on the first filtered data, the second filtered data, the third filtered data, and the three-dimensional position data. The gait analysis results include stride length, stride width, stride frequency, gait rhythm, gait periodicity, gait stability, and gait coordination.

[0044] The beneficial effects of the technical solutions provided in this application include at least the following:

[0045] This application provides a gait analysis system and method. The gait analysis system includes multiple inertial measurement modules for detecting acceleration and angular velocity data of the user's central torso, lateral knees, and lateral ankles; multiple infrared depth cameras for detecting pressure data of the user's feet; an infrared depth camera for detecting depth image data of the user's movement; an optical motion capture module for acquiring the user's three-dimensional position data; a data filtering module for classifying and filtering the data detected by the above devices; and a main control module. Through the cooperation of multiple modules, various types of data reflecting gait characteristics are acquired. The data can compensate for each other and collaboratively reflect the user's gait characteristics. Finally, the main control module obtains the user's gait analysis results, realizing a comprehensive analysis of the user's stride length, stride width, stride frequency, gait rhythm, gait periodicity, gait stability, and gait coordination. This gait analysis system can eliminate the problem of inaccurate gait analysis caused by the limited information collected by a single sensor, reduce the error interference of external environmental influences on gait analysis, improve detection accuracy and reliability, and achieve accurate and comprehensive analysis of the user's gait. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 This is a schematic diagram of the gait analysis system provided in the embodiments of this application;

[0048] Figure 2 A flowchart illustrating the gait analysis method provided in this application embodiment.

[0049] The reference numerals in the figure are respectively:

[0050] 1-Inertial measurement module, 2-Pressure measurement module, 3-Infrared depth camera, 4-Optical motion capture module, 41-Optical motion capture camera, 42-Reflective marker. Detailed Implementation

[0051] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0052] To make the technical solutions and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0053] This application provides a gait analysis system, referring to... Figure 1 The gait analysis system includes multiple inertial measurement modules 1, multiple pressure measurement modules 2, an infrared depth camera 3, an optical motion capture module 4, a data filtering module, and a main control module.

[0054] Multiple inertial measurement modules 1 are used to detect acceleration and angular velocity data at the center of the user's torso, the outer sides of both knees, and the outer sides of both ankles. The inertial measurement modules 1 are important detection modules of the gait analysis system provided in this application embodiment. Located at the center of the user's torso, the outer sides of both knees, and the outer sides of both ankles, they detect the acceleration and angular velocity data of the corresponding body parts, reflecting the user's movement. The acceleration data reflects the acceleration and deceleration of the torso in the forward / backward and left / right directions. The angular velocity data reflects the rotational speed of the torso along each axis (forward / backward, left / right, up / down).

[0055] In some embodiments, the inertial measurement module 1 includes an accelerometer and a gyroscope, which are used to detect acceleration data and angular velocity data, respectively.

[0056] Multiple pressure measurement modules 2 are used to detect pressure data on the soles of the user's feet. The pressure measurement module 2 is an important detection module of the gait analysis system provided in this application embodiment. It is located on the soles of the user's feet and can comprehensively detect the pressure distribution on the soles of the user's feet during the user's walking process.

[0057] In some embodiments, the pressure measurement module 2 can be a pressure sensor, and multiple pressure measurement modules 2 form an array located at different positions on the user's sole. This array can comprehensively detect the pressure distribution on the user's sole, accurately measure sole pressure, and identify the gait cycle, including various stages such as landing, support, and push-off. This is the basis for analyzing the user's foot health status and gait characteristics.

[0058] The infrared depth camera 3 is positioned in front of or to the side of the user to detect depth image data of the user's movement. The infrared depth camera 3 generates a depth image of the user by actively emitting infrared light and receiving reflected light, covering the entire field of vision of the human body and capturing the user's movement trajectory.

[0059] The optical motion capture module 4 is used to collect high-precision three-dimensional position data of the user. The optical motion capture module 4 is located around the user. The high-precision three-dimensional position data of the user collected by the optical motion capture module 4 can not only serve as a correction standard for the data collected by other measurement modules, but also supplement the capture deficiencies of other measurement modules. Through cooperation with other modules, it can collect various types of data that can reflect gait characteristics. The data can compensate for each other and collaboratively reflect the user's gait characteristics, so that the gait analysis system provided in this application embodiment can comprehensively capture the user's motion information and thus achieve accurate gait analysis.

[0060] The optical motion capture module 4 may include multiple optical motion capture cameras 41 placed around the user, multiple reflective markers 42 placed at the joints of the user's lower body, a POE+ switch, and a calibration rod.

[0061] With this setup, the optical motion capture module 4 features a high-resolution and high-frame-rate optical motion capture camera that captures the user's fine motion trajectory from multiple perspectives, avoiding obstructions and blind spots.

[0062] In some embodiments, reflective markers 42 positioned at key joint points of the user's lower body can be located on the instep, heel, ankle, calf, knee, thigh, lower abdomen, or lower back. These locations are chosen because the reflective markers 42 can accurately capture the user's joint movement trajectory during walking. By distributing multiple reflective markers 42 at key locations on the user's lower limbs, comprehensive and accurate analysis of the user's gait can be achieved. Simultaneously, the user's lower body model can be reconstructed in the main control module, and further gait analysis can be performed using the model and data.

[0063] In some embodiments, in order to ensure the wearing effect of the reflective marker 42, the reflective marker 42 can be fixed to the joint point of the user's lower body corresponding to the nylon clothing, thereby ensuring the reflective effect of the reflective marker 42 and the acquisition effect of the optical motion capture module 4.

[0064] The PoE+ switch in the optical motion capture module 4 is connected to the main control module and is used to send the high-precision three-dimensional position data collected by the optical motion capture cameras 41 to the main control module for subsequent gait analysis. The calibration rods in the optical motion capture module 4, including L-shaped and T-shaped calibration rods, are used to calibrate multiple optical motion capture cameras 41, ensuring that they work synchronously and guaranteeing the accuracy and consistency of the position data of the reflective markers 42 captured by the multiple optical motion capture cameras 41.

[0065] The data acquired by the inertial measurement module 1, the pressure measurement module 2, and the infrared depth camera 3 may contain interference, requiring reduction of data noise and removal of invalid data. The gait analysis system provided in this application includes a data filtering module. This module can perform bandpass filtering on acceleration and angular velocity data to obtain first filtered data, low-pass filtering on pressure data to obtain second filtered data, and weighted average filtering on depth image data to obtain third filtered data.

[0066] In some embodiments, the filtering processing of acceleration and angular velocity data acquired by the inertial measurement module 1 includes: (1) Bandpass filtering: A Butterworth bandpass filter is used, with a cutoff frequency set from 0.1 Hz to 20 Hz. This filter combines the effects of high-pass and low-pass filtering, eliminating high-frequency noise and low-frequency drift, while retaining effective motion signals and rapidly changing motion characteristics. (2) Kalman filtering: Smoothing processing improves the accuracy and reliability of the data. The state model and measurement model of the Kalman filter are designed according to the characteristics of the inertial measurement module 1, thereby effectively filtering the acceleration and angular velocity data acquired by the inertial measurement module 1.

[0067] In some embodiments, the filtering processing of the depth image data acquired by the infrared depth camera 3 includes: (1) Spatial filtering: removing noise from the depth image data and enhancing its clarity by using a Gaussian filter for smoothing. (2) Temporal filtering: smoothing the depth image data between consecutive frames and eliminating instantaneous noise. A weighted average filter is used to perform a weighted average of the depth data of the current frame and the previous few frames.

[0068] In some embodiments, the filtering process for the pressure data acquired by the pressure measurement module 2 includes: low-pass filtering: removing high-frequency noise and retaining valid pressure data. A Butterworth low-pass filter is used, with a cutoff frequency set to 10Hz.

[0069] The main control module is the core processing and analysis module of the gait analysis system provided in this application embodiment, and it is the center of data collection and processing. The main control module is used to determine the user's gait analysis results based on the first filtered data, the second filtered data, the third filtered data, and the three-dimensional position data. The gait analysis results include stride length, stride width, stride frequency, gait rhythm, gait periodicity, gait stability, and gait coordination.

[0070] In some embodiments, the main control module includes a feature extraction unit, which includes a first feature extraction subunit, a second feature extraction subunit, a third feature extraction subunit, and a fourth feature extraction subunit.

[0071] The first feature extraction subunit is used to determine the motion features of the user's torso and the forward, backward, left, and right tilt features of the torso based on the first filtered data.

[0072] In some embodiments, the motion and tilt characteristics of the user's torso include linear motion characteristics and angular motion characteristics. Linear motion characteristics are determined based on acceleration and angular velocity data. The acceleration peaks, deceleration troughs, average values, and standard deviations of the acceleration data reflect the acceleration and deceleration of the torso in the forward / backward and left / right directions. Velocity data is obtained by integrating the acceleration data; the average value, maximum value, and fluctuations of the velocity data reflect the velocity changes of the torso in the forward / backward and left / right directions. Displacement data is obtained by integrating the velocity data; the displacement data reflects the displacement changes within the gait cycle and can be used to analyze stride length and stride frequency. Angular motion characteristics are determined based on angular velocity data. The rotational peaks, average values, and standard deviations of the angular velocity data reflect the rotational velocity of the torso along each axis (forward / backward, left / right, up / down). The angle data is obtained by integrating the angular velocity data; the angle data reflects the rotational angle changes within the gait cycle and is used to analyze the overall rotational characteristics of the torso.

[0073] In some embodiments, the first feature extraction subunit is specifically used for: (1) identifying key points in the gait cycle based on the time-domain features of the first filtered data using a peak detection algorithm, so as to analyze the gait cycle, step length, step frequency, and gait rhythm in the future. (2) analyzing the frequency-domain features of the first filtered data through Fourier transform and extracting the spectral features of the gait, so as to facilitate subsequent gait analysis based on the spectral features of the gait. (3) calculating the average value, standard deviation, peak value, and other statistical features of the acceleration and angular velocity data in the first filtered data, so as to determine the motion characteristics of the user's torso and the forward, backward, left, and right tilting characteristics of the torso.

[0074] The second feature extraction subunit is used to determine the pressure distribution, pressure changes, and pressure dynamic characteristics of the user's sole based on the second filtered data.

[0075] In some embodiments, the second feature extraction subunit is specifically used for: (1) extracting plantar pressure distribution features and pressure change features based on the second filtered data, including pressure distribution and pressure change at different time stages, to facilitate subsequent analysis of the maximum pressure point, average pressure, and pressure center trajectory. (2) extracting statistical features such as the mean, standard deviation, and peak value of the second filtered data to determine the dynamic characteristics of plantar pressure.

[0076] The third feature extraction subunit is used to determine the motion trajectory of the joints based on the third filtered data.

[0077] In some embodiments, the third feature extraction subunit is specifically used for: determining the user skeleton and skeleton position change information based on the third filtered data; and determining the joint motion trajectory based on the user skeleton and skeleton position change information. Through the third feature extraction subunit, the motion trajectory of each joint point of the user during movement can be accurately captured and determined, providing detailed data support for gait analysis.

[0078] It should be noted that the infrared depth camera 3 and the optical motion capture module 4 each have their own characteristics and advantages in motion trajectory capture. The infrared depth camera 3 acquires three-dimensional depth information, i.e., depth image data, by emitting infrared light and calculating the reflection time or distortion of the reflected image. This allows it to construct the user's three-dimensional model and skeleton information. The infrared depth camera 3 can quickly capture the user's skeleton information and joint movement trajectory without complex markings, making it suitable for real-time monitoring and analysis, and offering high flexibility and convenience. The optical motion capture module 4, on the other hand, places multiple reflective markers 42 on the user and uses multiple optical motion capture cameras 41 to simultaneously capture the positional changes of the reflective markers 42. Triangulation is used to determine the three-dimensional coordinates of the reflective markers 42, i.e., three-dimensional position data, thereby obtaining the user's joint movement trajectory. The optical motion capture module 4 can capture the user's subtle movements with high precision, making it particularly suitable for applications requiring high-precision and detailed motion analysis. By combining the advantages of both, comprehensive and accurate analysis of the user's motion trajectory can be achieved, providing reliable data support for gait analysis.

[0079] The fourth feature extraction subunit is used to determine the tracking position and trajectory of the marker point based on the three-dimensional position data, which facilitates subsequent analysis of gait stability and gait coordination.

[0080] In some embodiments, the main control module includes a multimodal data fusion unit, which includes a first data fusion unit and a second data fusion unit.

[0081] The first data fusion unit is used to fuse the motion characteristics of the user's torso, the forward, backward, left and right tilt characteristics of the torso, the pressure distribution, pressure changes and pressure dynamic characteristics of the user's feet to obtain the first fused data.

[0082] In some embodiments, the fusion process includes feature-level fusion and decision-level fusion. Feature-level fusion integrates the user's torso motion characteristics, torso tilt characteristics (forward, backward, left, and right), and pressure distribution, pressure changes, and pressure dynamics of the user's feet to obtain a comprehensive feature vector. Feature-level fusion captures the interrelationships and comprehensive features between various data sources, facilitating subsequent overall analysis. Decision-level fusion, based on preliminary analysis and judgment of the user's torso motion characteristics, torso tilt characteristics (forward, backward, left, and right), and pressure distribution, pressure changes, and pressure dynamics of the user's feet, then integrates the results of each analysis to obtain an accurate comprehensive judgment. This fusion method fully utilizes the independent information from each data source, improving the accuracy and reliability of the fusion results.

[0083] The second data fusion unit is used to fuse the joint motion trajectory and three-dimensional position data to obtain the second fused data.

[0084] In some embodiments, the fusion process of the second data fusion unit is to combine these features together using multimodal fusion algorithms such as weighted average and Kalman filtering.

[0085] In some embodiments, the main control module includes a gait analysis unit and a motion performance evaluation unit.

[0086] The gait analysis unit is used to determine stride length, stride width, stride frequency, gait rhythm, and gait periodicity based on the first fusion data, and to determine gait stability and gait coordination based on the second fusion data.

[0087] The athletic performance assessment unit generates an athletic performance assessment report based on stride length, stride frequency, gait rhythm, gait periodicity, gait stability, and gait coordination. The report includes a visual atlas of stride length, stride length, stride frequency, gait rhythm, gait periodicity, gait stability, and gait coordination, as well as athletic strengths and gait improvement suggestions. Users can use the athletic performance assessment report to develop athletic training strategies, improve gait, and enhance athletic performance.

[0088] It's important to note that stride length is the distance between the two adjacent points of contact of a user's feet during race walking or running. It's a crucial factor determining walking and running speed, usually expressed in meters per step. Stride length is primarily determined by leg length, the force and angle of the push-off, hip joint flexibility, and the coordination of various body parts. Stride length is the distance of one step, measured from the center of the foot. The distance between the centers of the two feet after one step is the stride length. Cadence refers to the number of times the legs alternate per unit of time during race walking or running. Gait rhythm refers to the ratio between the number of steps taken per minute and the walking beat. In a normal gait, the gait rhythm is typically 1:1, meaning each step is accompanied by one beat. Gait periodicity refers to the cyclical process of the same foot moving from heel to heel strike during walking. Each completion of this process constitutes one gait cycle. Gait periodicity includes the foot contact phase, stance phase, push-off phase, and swing phase. Gait stability refers to the stability of a user's body during walking, that is, whether the body can move smoothly. Gait coordination refers to the coordinated movement between different parts of the body during walking.

[0089] To enhance user experience and achieve accurate and comprehensive analysis of user gait, in some embodiments, the main control module further includes an anomaly detection and analysis unit, which is used for:

[0090] (1) Based on the user’s trunk motion characteristics, trunk tilt characteristics, pressure distribution, pressure changes, pressure dynamic characteristics, joint movement trajectory, and three-dimensional position data, abnormal features and abnormal locations are determined. Abnormal features include gait asymmetry, excessive stride length, excessive stride length, and unstable gait.

[0091] (2) Based on abnormal features, generate a gait abnormality report. The gait abnormality report includes abnormal features, abnormal locations and gait improvement suggestions, so that users can understand their own gait status and correct bad gait habits in a timely manner.

[0092] To improve the detection accuracy and reliability of gait analysis, the three-dimensional position data of the user collected by the optical motion capture module 4 with high detection accuracy is used to compensate and correct the data collected by other measurement modules. In some embodiments, the main control module also includes a compensation and correction unit, which is specifically used for:

[0093] (1) Eliminate data drift of inertial measurement module 1, and perform error compensation and correction on inertial measurement module 1 based on three-dimensional position data. Compare the motion trajectory of the user's torso, knees and ankles in the three-dimensional position data with the acceleration and angular velocity data of the user's torso center, the outer sides of both knees and the outer sides of the left and right ankles detected by inertial measurement module 1, adjust the bias of inertial measurement module 1 to eliminate data drift, and perform error compensation and correction on inertial measurement module 1.

[0094] In some embodiments, the above steps are implemented as follows: First, the acceleration is integrated to obtain velocity and position data. The obtained position data is then compared with the three-dimensional position data to obtain errors and deviations. Based on these errors and deviations, an error model is established, incorporating various error sources such as bias error, scaling factor error, and noise error. Then, the bias parameters of the inertial measurement module 1 are adjusted using the bias error in the error model. Specifically, the three-dimensional position data is used as a reference. The acceleration and angular velocity data at each time point are compared to calculate the error at each time point. The global bias is calculated by accumulating the error, and the bias parameters of the inertial measurement module 1 are dynamically adjusted to ensure that the zero bias of the acceleration and angular velocity data remains stable within the minimum error range. Finally, the measurement accuracy is improved by real-time error compensation. Specific error compensation methods include combining inertial measurement data and three-dimensional position data in a Kalman filter to update and correct the state estimate in real time. Kalman gain is used to correct noise and random errors in the inertial measurement data, achieving higher precision acceleration and angular velocity data.

[0095] (2) Based on the three-dimensional position data, the sensitivity and response time of the pressure measurement module 2 are corrected, and the phase of the pressure measurement module 2 is adjusted based on the gait cycle data in the three-dimensional position data.

[0096] In some embodiments, three-dimensional position data is compared with plantar pressure distribution data recorded by pressure measurement module 2 to determine the response of pressure measurement module 2 at different gait stages. By analyzing the movement trajectories of the trunk, knees, and ankles, key points in the gait cycle, such as plantar contact and takeoff times, can be identified. Sensitivity correction is performed by calculating the correlation between the output of pressure measurement module 2 and actual position changes within each gait cycle, and adjusting the gain coefficient of pressure measurement module 2 to match actual pressure changes. Response time correction is performed by analyzing key time points (such as plantar contact and takeoff times) in the three-dimensional position data and adjusting the response time parameters of pressure measurement module 2 to eliminate delays or advances. Phase adjustment specifically aligns the output of pressure measurement module 2 with key events in the gait cycle (such as heel strike, total plantar contact, etc.) to ensure that the time axis of the data detected by pressure measurement module 2 is consistent with the actual gait cycle, thereby achieving synchronization between the output of pressure measurement module 2 and the actual gait cycle.

[0097] (3) Correct the depth image parameters of the infrared depth camera and adjust the accuracy of the depth image data based on the three-dimensional position data.

[0098] In some embodiments, the above steps are implemented as follows: First, the root mean square error (RMSE) between the 3D position data and the depth image parameters is calculated to quantify the accuracy deviation of the depth image data. By focusing on the errors within different depth ranges, it is determined whether depth range-dependent errors exist. Then, based on the RMSE, a correction function is used to adjust the depth image data for linear or nonlinear correction to correct systematic deviations.

[0099] Data detected by various types of measurement modules is multimodal, requiring data integration before processing. In some embodiments, the main control module further includes a data integration unit for integrating acceleration data, angular velocity data, pressure data, depth image data, and 3D position data to ensure data comprehensiveness and consistency, thereby improving the accuracy of gait analysis.

[0100] In some embodiments, data integration includes data synchronization, specifically implemented by aligning the timestamps of all data sources to ensure that different types of data are consistent in time. Through timestamp interpolation or time synchronization algorithms, it is ensured that acceleration data, angular velocity data, pressure data, depth image data, and 3D position data all reflect the state at the same point in time or within the same time period.

[0101] To improve the efficiency and response speed of real-time data processing, in some embodiments, the main control module also includes a data segmentation unit, which is used to segment the acceleration data, angular velocity data, pressure data, depth image data and three-dimensional position data. The segmentation process involves segmenting the integrated acceleration data, angular velocity data, pressure data, depth image data and three-dimensional position data once every threshold time interval to obtain segmented data.

[0102] In some embodiments, the threshold duration can be 5 seconds.

[0103] For example, taking the integrated pressure data as an example, the integrated pressure data is divided into segments every 5 seconds, and each segment contains sampling points of all pressure data within 5 seconds. According to the sampling frequency of the inertial measurement module 1 of 60Hz, each segment of the data contains 300 data points.

[0104] In summary, the gait analysis system provided in this application can eliminate the problem of inaccurate gait analysis caused by the limited amount of information that a single sensor can collect, reduce the error interference of external environmental influences on gait analysis, improve detection accuracy and reliability, and achieve accurate and comprehensive analysis of the user's gait.

[0105] Secondly, embodiments of this application provide a gait analysis method, see [link to relevant documentation]. Figure 2 The gait analysis method includes:

[0106] Step 201: Multiple inertial measurement modules 1 detect acceleration and angular velocity data of the user's central torso, the outer sides of both knees, and the outer sides of both ankles.

[0107] Step 202: Multiple pressure measurement modules 2 detect pressure data on the user's soles.

[0108] Step 203: Infrared depth camera 3 detects depth image data of user movement.

[0109] Step 204: The optical motion capture module 4 acquires the user's three-dimensional position data.

[0110] Step 205: The data filtering module performs bandpass filtering on the acceleration data and angular velocity data to obtain the first filtered data, performs low-pass filtering on the pressure data to obtain the second filtered data, and performs weighted average filtering on the depth image data to obtain the third filtered data.

[0111] Step 206: The main control module determines the user's gait analysis results based on the first filtered data, the second filtered data, the third filtered data, and the three-dimensional position data. The gait analysis results include stride length, stride width, stride frequency, gait rhythm, gait periodicity, gait stability, and gait coordination.

[0112] In summary, the gait analysis method provided in this application can eliminate the problem of inaccurate gait analysis caused by the limited amount of information that a single sensor can collect, reduce the error interference of external environmental influences on gait analysis, improve detection accuracy and reliability, and achieve accurate and comprehensive analysis of user gait.

[0113] In this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance. The term "multiple" refers to two or more unless otherwise expressly defined.

[0114] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only.

[0115] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A gait analysis system, characterized in that, The gait analysis system includes: Multiple inertial measurement modules (1) are used to detect acceleration and angular velocity data of the user's central torso, the outer sides of both knees and the outer sides of the left and right ankles; Multiple pressure measurement modules (2) are used to detect pressure data on the user's soles; Infrared depth camera (3) is used to detect depth image data of user movement; optical motion capture module (4) is used to collect three-dimensional position data of user, including multiple optical motion capture cameras (41) set around the user, multiple reflective markers (42) set at the joints of the user's lower body, POE+ switch and calibration rod; The data filtering module is used to perform bandpass filtering on the acceleration data and the angular velocity data to obtain first filtered data, low-pass filtering on the pressure data to obtain second filtered data, and weighted average filtering on the depth image data to obtain third filtered data. The main control module is used to determine the user's gait analysis results based on the first filtered data, the second filtered data, the third filtered data, and the three-dimensional position data. The gait analysis results include stride length, stride width, stride frequency, gait rhythm, gait periodicity, gait stability, and gait coordination. The main control module includes a compensation and correction unit, which is specifically used to: eliminate the data drift of the inertial measurement module (1) and perform error compensation and correction on the inertial measurement module (1) based on the three-dimensional position data; correct the sensitivity and response time of the pressure measurement module (2) based on the three-dimensional position data and perform phase adjustment on the pressure measurement module (2) based on the gait period data in the three-dimensional position data; and correct the depth image parameters of the infrared depth camera and adjust the accuracy of the depth image data based on the three-dimensional position data.

2. The gait analysis system according to claim 1, characterized in that, The main control module includes a feature extraction unit, which includes a first feature extraction subunit, a second feature extraction subunit, a third feature extraction subunit, and a fourth feature extraction subunit. The first feature extraction subunit is used to determine the motion features of the user's torso and the forward, backward, left, and right tilt features of the torso based on the first filtered data. The second feature extraction subunit is used to determine the pressure distribution, pressure changes, and pressure dynamic characteristics of the user's sole based on the second filtered data; The third feature extraction subunit is used to determine the motion trajectory of the joints based on the third filtered data; The fourth feature extraction subunit is used to determine the tracking position and motion trajectory of the marker point based on the three-dimensional position data.

3. The gait analysis system according to claim 2, characterized in that, The main control module includes a multimodal data fusion unit, which includes a first data fusion unit and a second data fusion unit. The first data fusion unit is used to fuse the motion characteristics of the user's torso, the forward, backward, left and right tilt characteristics of the torso, the pressure distribution of the user's soles, the pressure changes, and the pressure dynamic characteristics to obtain the first fused data. The second data fusion unit is used to fuse the joint motion trajectory, the marker tracking position, and the marker motion trajectory to obtain second fused data.

4. The gait analysis system according to claim 3, characterized in that, The main control module includes a gait analysis unit and a motion performance evaluation unit; The gait analysis unit is used to determine stride length, stride width, stride frequency, gait rhythm, and gait periodicity based on the first fused data, and to determine gait stability and gait coordination based on the second fused data. The sports performance evaluation unit is used to generate a sports performance evaluation report based on stride length, stride frequency, gait rhythm, gait periodicity, gait stability, and gait coordination. The sports performance evaluation report includes a visualization of stride length, stride length, stride frequency, gait rhythm, gait periodicity, gait stability, and gait coordination, as well as sports advantages and gait improvement suggestions.

5. The gait analysis system according to claim 3 or 4, characterized in that, The main control module further includes an anomaly detection and analysis unit, which is used for: Based on the user's torso movement characteristics, the torso's forward, backward, left, and right tilt characteristics, the user's foot pressure distribution, pressure changes, pressure dynamic characteristics, joint movement trajectories, and three-dimensional position data, abnormal features and abnormal locations are determined. The abnormal features include gait asymmetry, excessive stride length, excessive stride length, and gait instability. Based on the abnormal features, a gait abnormality report is generated, which includes the abnormal features, the abnormal location, and gait improvement suggestions.

6. The gait analysis system according to claim 1, characterized in that, The calibration rods include L-shaped calibration rods and T-shaped calibration rods, which are used to calibrate multiple optical motion capture cameras (41) so that the multiple optical motion capture cameras (41) work synchronously.

7. The gait analysis system according to any one of claims 1-6, characterized in that, The main control module also includes a data integration unit and a data segmentation unit; The data integration unit is used to integrate the acceleration data, the angular velocity data, the pressure data, the depth image data, and the three-dimensional position data; The data segmentation unit is used to segment the integrated acceleration data, angular velocity data, pressure data, depth image data, and three-dimensional position data. The segmentation process involves segmenting the integrated acceleration data, angular velocity data, pressure data, depth image data, and three-dimensional position data once at every threshold time interval to obtain segmented data.

8. A gait analysis method, characterized in that, The gait analysis method includes: Multiple inertial measurement modules (1) detect acceleration and angular velocity data at the center of the user's torso, the outer sides of both knees, and the outer sides of the left and right ankles; Multiple pressure measurement modules (2) detect pressure data on the user's soles; Infrared depth camera (3) detects depth image data of user movement; The optical motion capture module (4) collects the user's three-dimensional position data; The data filtering module performs bandpass filtering on the acceleration data and the angular velocity data to obtain first filtered data, performs low-pass filtering on the pressure data to obtain second filtered data, and performs weighted average filtering on the depth image data to obtain third filtered data. The main control module determines the user's gait analysis results based on the first filtered data, the second filtered data, the third filtered data, and the three-dimensional position data. The gait analysis results include stride length, stride width, stride frequency, gait rhythm, gait periodicity, gait stability, and gait coordination.

Images