Gait analysis method and system based on intelligent shoes

Abstract

The invention relates to the field of gait analysis, and discloses a gait analysis method and system based on intelligent shoes, and the method comprises the steps: obtaining pressure distribution data captured by a plantar pressure sensor, dividing gait stages according to a pressure mode, and recognizing gait phases; the method comprises the following steps: acquiring three-dimensional acceleration, angular velocity and magnetic field data of an inertial measurement unit, and converting the three-dimensional acceleration data from an IMU coordinate system to an earth coordinate system; performing integral calculation on the three-dimensional acceleration data based on the earth coordinate system to obtain speed data; describing the time stage of the gait through the pressure mode of the pressure distribution data, detecting to obtain a zero speed moment, correcting the speed data by applying a zero speed updating algorithm according to the zero speed moment to obtain the corrected speed data, and further performing integral calculation to obtain the motion trail of the foot; through a principal component analysis algorithm, decoupling the displacement in the step length direction and the step width direction in the foot motion trail so as to obtain step length and step width parameters; the plantar pressure distribution data cloud picture and the foot movement track are combined and visualized, visual reproduction of the foot posture in the gait process is completed, and a convenient mode is provided for a patient to monitor and evaluate the gait health condition of the patient.

Description

Technical Field

[0001] The present invention relates to the field of gait analysis, and in particular to a gait analysis method and system based on smart shoes. Background Art

[0002] Gait analysis plays an important role in the quantitative assessment of locomotor system diseases, especially gait disorders caused by musculoskeletal diseases and neurological diseases. Studies have shown that changes in gait parameters, such as gait speed, step length, step width, gait cycle, plantar pressure pattern, etc., can better reflect the severity of patients with musculoskeletal diseases such as chronic ankle instability, osteoarthritis, flat feet, equinus deformity, and are also closely related to neurological diseases such as Parkinson's disease and stroke. As an important diagnostic method, gait analysis has been widely used in the diagnosis and evaluation of related diseases and postoperative rehabilitation. However, the current clinical gait analysis mainly relies on the traditional "visual inspection" method combined with the doctor's experience and subjective judgment for diagnosis.

[0003] Currently, commercial gait analysis equipment can accurately collect and analyze patients' gait data. For example, the optical motion capture system VICON attaches reflective markers to the subject and uses multiple cameras to capture motion data to calculate the motion trajectory of various parts of the body; the force plate AMTI is used to measure the force interaction between the foot and the ground during walking, including vertical force, shear force, etc.; the electronic walkway GAITRite is a portable gait analysis tool that records the position, time and pressure distribution of foot contact through a sensor array embedded in the floor mat. However, these devices are usually costly, complicated to use, difficult to analyze data, and require professional technicians to operate. These factors limit their application in daily life and clinical practice, resulting in a shortage of high-quality, large-scale gait data related to clinical diseases, making it difficult to provide effective big data support for clinicians.

[0004] With the development of micro-inertial measurement unit (IMU) technology, many researchers have tried to obtain gait parameters through IMU-based wearable devices. One method is to establish the correlation between gait parameters and inertial sensor measurements through machine learning. However, this method is not easy to apply to people with abnormal gait or large differences in gait function. Another method is to directly integrate acceleration and angular velocity data to obtain the displacement and direction of the footsteps. The direct integration method is basically not affected by the user's abnormal gait pattern. However, the drift problem of inertial sensors is still difficult to solve. Studies have shown that directional drift can be reduced by Kalman filter data fusion, and acceleration drift can be solved by the zero velocity update (ZUPT) algorithm. In addition, current IMU-based wearable devices are usually unable to obtain dynamic data, especially dynamic plantar pressure analysis, which significantly limits its clinical application. Summary of the invention

[0005] The main purpose of the present invention is to solve the technical problem that the dynamic plantar pressure analysis effect is not good in the prior art. A gait analysis method based on smart shoes includes the following steps:

[0006] Acquire pressure distribution data captured by a plantar pressure sensor, divide gait phases according to a time pattern, and identify gait phases, wherein the identified gait phases are obtained by foot contact detection and toe-off detection, and the gait phases include a stance phase and a swing phase;

[0007] Obtain the three-dimensional acceleration, angular velocity and magnetic field data of the inertial measurement unit, convert the three-dimensional acceleration data from the IMU coordinate system to the earth coordinate system, and obtain the three-dimensional acceleration data based on the earth coordinate system;

[0008] Initial velocity data is obtained by integrating the three-dimensional acceleration data based on the earth coordinate system, and the time stage of gait is depicted by the pressure pattern of the pressure distribution data, and the zero velocity moment is detected, and zero velocity update is applied to the initial velocity data according to the zero velocity moment, and the error caused by inertial sensor noise and signal drift is corrected to obtain the corrected velocity data.

[0009] The movement trajectory of the foot is obtained by performing a second integral calculation on the corrected speed data.

[0010] Through the principal component analysis algorithm, the step length and step width displacement in the foot motion trajectory are decoupled to obtain the step length and step width parameters.

[0011] By combining the plantar pressure distribution data cloud map with the foot motion trajectory and visualizing them, the visual reproduction of the foot posture during the gait process is completed.

[0012] The gait analysis method further comprises a foot deviation angle estimation step:

[0013] According to the movement trajectory of the foot, the pressure center point at the heel is calculated each time the heel touches the ground, and the pressure center point at the metatarsal is calculated when pushing off. The angle between the line connecting the two pressure center points and the forward direction is the foot deviation angle.

[0014] The foot contact detection method is:

[0015] The moment when the foot touches the ground is detected by monitoring the vertical ground reaction force (vGRF) from the pressure sensor. When the vGRF exceeds a predetermined threshold, it is recognized that the foot has touched the ground. The formula is as follows:

[0016]

[0017] Among them, vGRF i is the plantar pressure, vGRF threshold is the sensor pressure threshold.

[0018] The toe-off detection method is as follows:

[0019] When the vGRF is lower than a predetermined threshold, a foot-off event is detected, indicating that the foot is leaving the ground;

[0020]

[0021] Through foot contact detection and toe-off detection, the various phases of the gait cycle are identified, thereby performing gait phase segmentation.

[0022] The method for calculating the pressure center point CoP when the heel touches the ground is as follows: using the plantar pressure sensor data, identifying the pressure distribution when the heel touches the ground, and calculating the position of the pressure center point at this time according to the pressure distribution diagram;

[0023] The method for calculating the pressure center point CoP' at the metatarsal during push-off is: also using the plantar pressure sensor data, identifying the pressure distribution during push-off, and calculating the pressure center point position at this time according to the pressure distribution diagram.

[0024] The calculation method of the foot deflection angle is:

[0025] The foot deflection angle is obtained by calculating the angle between the line between CoP and CoP' and the forward direction. The formula is as follows:

[0026]

[0027] Where θ is the foot deflection angle, CoP x and CoP yRespectively represent the x and y coordinates of the center of pressure at the heel, CoP' x and CoP' y Respectively represent the x and y coordinates of the center of pressure at the metatarsal bones.

[0028] The three-dimensional acceleration data is converted from the IMU coordinate system to the earth coordinate system as follows:

[0029] The acceleration vector a in the IMU coordinate system IMU The acceleration vector a converted to the Earth coordinate system earth The formula is:

[0030] a earth =R·a IMU

[0031] Among them, R is the rotation matrix, and the calculation formula of R is:

[0032] R=R z (Ψ)R y (θ)R x (Φ)

[0033] Among them, R x (Φ), R y (θ) and R z (Ψ) are the rotation matrices around the x-axis, y-axis, and z-axis, respectively, and can be expressed as:

[0034]

[0035] A second aspect of the present invention provides a gait analysis system based on smart shoes, comprising:

[0036] A gait phase division unit, used to obtain pressure distribution data captured by a plantar pressure sensor, divide the gait phase according to a time pattern, and identify the gait phase, wherein the identified gait phase is obtained by foot contact detection and toe-off detection, and the gait phase includes a support phase and a swing phase;

[0037] An acceleration conversion unit is used to obtain the three-dimensional acceleration, angular velocity and magnetic field data of the inertial measurement unit, convert the three-dimensional acceleration data from the IMU coordinate system to the earth coordinate system, and obtain the three-dimensional acceleration data based on the earth coordinate system;

[0038] A zero speed update unit is used to obtain initial speed data by integrating the three-dimensional acceleration data based on the earth coordinate system, determine the zero speed moment in the gait by combining the pressure pattern of the plantar pressure distribution data, and then apply the zero speed update algorithm to correct the error accumulation caused by the inertial sensor noise and signal drift to obtain the corrected speed data;

[0039] The motion trajectory calculation unit is used to obtain the motion trajectory of the foot by integrating the corrected speed data.

[0040] The stride and step length decoupling unit is used to obtain the vectors of the stride length direction and the step width direction during walking by applying the principal component analysis algorithm to the foot motion trajectory, and then project the foot motion trajectory along the stride length direction vector and the step width direction vector respectively to complete the decoupling of the stride length and step width data and obtain the stride length and step width parameters in the gait.

[0041] The visualization unit combines and visualizes the plantar pressure distribution data cloud map with the foot movement trajectory to complete the visualization reproduction of the foot posture during the gait process.

[0042] The third aspect of the present invention provides an electronic device, comprising: a memory and at least one processor, wherein instructions are stored in the memory, and the memory and the at least one processor are interconnected via lines; the at least one processor calls the instructions in the memory so that the electronic device executes the above-mentioned gait analysis method based on smart shoes.

[0043] A fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the above-mentioned gait analysis method based on smart shoes.

[0044] The present invention has the following beneficial effects:

[0045] The present invention integrates an inertial navigation unit and a wearable gait spatiotemporal parameter analysis system with in-shoe thin-film pressure sensing technology, which can complete non-contact gait data collection and analysis at the minute level. The pressure sensor is placed in the shoe to accurately distinguish the gait phase and obtain the plantar pressure distribution data, especially in the time period when the walking speed reaches zero (mid-stance phase), so as to correct the error accumulation caused by inertial sensor noise and signal drift with the help of the ZUPT algorithm. The system can obtain a large amount of gait data with a low drift effect, realizing high-throughput collection of gait data. Its beneficial effects include:

[0046] 1. Cost-effectiveness and ease of use: Compared with gait analysis devices such as the Vicon optical motion capture system, AMTI force plate, and GAITRite electronic walkway, which are costly, complex to operate, and require use in specific experimental environments, the smart shoe system of the present invention provides a cost-effective and easy-to-use solution. The rapid collection and analysis of a few minutes will help promote the use of gait analysis.

[0047] 2. Richness of data types: Compared with the existing technology that mainly focuses on the measurement of kinematic parameters and has limited ability to obtain dynamic plantar pressure data, the smart shoe system of the present invention not only provides traditional gait kinematic parameters through the integrated insole-type plantar pressure sensor, but also can capture plantar pressure distribution data, providing more comprehensive information for disease diagnosis and evaluation.

[0048] 3. Real-time monitoring and environmental adaptability: In addition, the system integrates two IMUs and insole-type plantar pressure sensors into the shoes to minimize the additional impact of the equipment on the user, and supports long-term gait data collection in daily living environments. No specific laboratory environment and settings are required, so that gait analysis can be performed in a more realistic daily environment, providing more natural and accurate gait data.

[0049] 4. Through analytical algorithms, the sensor data is converted into basic gait data commonly used in clinical practice, such as step length, step height, plantar pressure distribution, support phase, swing phase, bilateral symmetry, etc., so that the system can be included in the same system with other gait analysis systems and traditional gait analysis in clinical practice so that doctors in clinical practice can understand, analyze and study it, rather than a closed black box system. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is the algorithm flow chart of the present invention;

[0051] Figure 2 It is a schematic diagram of foot deflection angle estimation of the present invention;

[0052] Figure 3 A schematic diagram of the bipedal posture visualization reproduction result provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0054] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1, the first embodiment of the gait analysis method based on smart shoes in the embodiment of the present invention includes:

[0055] Acquire pressure distribution data captured by a plantar pressure sensor, divide gait phases according to pressure patterns, and identify gait phases, wherein the identified gait phases are obtained through foot contact detection and toe-off detection, and the gait phases include a stance phase and a swing phase;

[0056] Obtain the three-dimensional acceleration, angular velocity and magnetic field data of the inertial measurement unit, convert the three-dimensional acceleration data from the IMU coordinate system to the earth coordinate system, and obtain the three-dimensional acceleration data based on the earth coordinate system;

[0057] The initial velocity data is obtained by integrating the three-dimensional acceleration data based on the earth coordinate system.

[0058] The time stage of gait is depicted by the pressure pattern of the pressure distribution data, the zero speed moment is detected, and the zero speed update is applied to the initial speed data according to the zero speed moment to correct the error caused by inertial sensor noise and signal drift to obtain the corrected speed data.

[0059] The movement trajectory of the foot is obtained by performing a second integral calculation on the corrected speed data.

[0060] Through the principal component analysis algorithm, the step length and step width displacement in the foot motion trajectory are decoupled to obtain the step length and step width parameters.

[0061] By combining the plantar pressure distribution data cloud map with the foot motion trajectory and visualizing them, the visual reproduction of the foot posture during the gait process is completed.

[0062] According to the movement trajectory of the foot, the pressure center point at the heel is calculated each time the heel touches the ground, and the pressure center point at the metatarsal is calculated when pushing off. The angle between the line connecting the two pressure center points and the forward direction is the foot deviation angle.

[0063] From the above steps, it can be seen that the foot position reconstruction algorithm used in the present invention mainly includes: (a) gait phase division, (b) direction estimation and acceleration transformation, (c) zero speed update, (d) trajectory calculation and step length and width decoupling, (e) foot deviation angle estimation. The algorithm flow chart is as follows Figure 1 shown.

[0064] First, using the pressure distribution data captured by the plantar pressure sensor, the gait phases are divided according to the time pattern, and the gait phases such as the stance phase and the swing phase are accurately identified.

[0065] Foot Contact (FC) Detection: The system detects the moment when the foot touches the ground by monitoring the vertical ground reaction force (vGRF) from the pressure sensor. A threshold-based algorithm is used to identify this event. When the vGRF exceeds a predetermined threshold, the system identifies that the foot has touched the ground.

[0066]

[0067] Among them, vGRF i is the plantar pressure, vGRF threshold is the sensor pressure threshold.

[0068] Toe Off (TO) detection: When vGRF is lower than a predetermined threshold, the system detects a toe off event, indicating that the foot is leaving the ground.

[0069]

[0070] Through these events, the various phases of the gait cycle can be clearly identified, thereby performing gait phase segmentation.

[0071] Secondly, by fusing the IMU's three-dimensional acceleration, angular velocity, and magnetic field data, the device's orientation relative to the Earth coordinate system is estimated. This process involves converting the roll, pitch, and yaw angles into rotation matrices, and then converting the acceleration data from the IMU coordinate system to the Earth coordinate system. As an efficient recursive filter, Kalman filtering can estimate the state of a dynamic system from a series of noisy measurement data. In IMU attitude estimation, the state of the system can be expressed by the orientation of the device, namely the roll, pitch, and yaw angles. The system state equation and measurement equation are:

[0072] Equation of state: X k =F k X k-1 +B k U k +W k

[0073] Measurement equation: Z k =H k X k +V k

[0074] Among them, X k is the current state (attitude angle), F k is the state transfer matrix, B k is the control input matrix, U k is the control input (usually 0 in IMU), W k is the process noise, Zk is the current measurement value (data from the accelerometer and magnetometer), H k is the measurement matrix, V k is the measurement noise. The roll, pitch, and yaw angles can be expressed as a rotation matrix to represent the orientation of the device. The rotation matrix R can be calculated from the roll (Φ), pitch (θ), and yaw (Ψ) angles as follows:

[0075] R=R z (Ψ)R y (θ)R x (Φ)

[0076] Among them, R x (Φ), R y (θ) and R z (Ψ) are the rotation matrices around the x-axis (roll), y-axis (pitch), and z-axis (yaw), respectively, which can be expressed as:

[0077]

[0078] Once the rotation matrix R is obtained, the acceleration vector a in the IMU coordinate system can be IMU The acceleration vector a converted to the Earth coordinate system earth :

[0079] a earth =R·a IMU

[0080] In this way, the acceleration vector in the earth coordinate system can be obtained. This step is critical for converting the IMU's acceleration data from the device coordinate system to a fixed reference coordinate system (such as the earth coordinate system), which allows the data to be interpreted according to the earth's gravity and magnetic field direction. Through the above steps, the Kalman filter can be used to combine the IMU's angular velocity, gravity vector, and magnetic field distribution data to effectively estimate the device's attitude and express it as roll, pitch, and yaw angles. These angles can then be converted into a rotation matrix, ultimately achieving the conversion of the acceleration data from the IMU coordinate system to the earth coordinate system. This process is critical for the accurate attitude estimation required for subsequent gait parameter calculations.

[0081] Third, the velocity is calculated by integrating the transformed acceleration at each step. A zero velocity update is then applied to subtract the drift error caused by sensor noise accumulation from the previously calculated velocity.

[0082] V corrected (t)=V(t)-V error

[0083] Among them, V erroris the velocity error detected by the zero velocity moment. The ZUPT algorithm essentially requires that the zero velocity moment be detected from repeated walking tests. Traditional foot-operated IMUs often have large displacement errors due to their poor detection capabilities for zero velocity segments. In this study, the temporal pattern of the pressure distribution data obtained in the shoe is used to depict the temporal phase of the gait, so that the zero velocity moment can be accurately detected. Finally, the motion trajectory of the foot is calculated by integrating the corrected velocity. Although the sensor fusion algorithm used previously obtains the motion of the IMU in the earth coordinate system, the motion of the IMU relative to the forward direction remains unknown. In order to decouple the displacement from the stride length direction and the step width direction, principal component analysis (PCA) is used. Through PCA, the main direction of the motion trajectory data can be found, which usually corresponds to the forward direction of walking. This distinguishes the displacement in the stride length direction from the displacement in the step width direction. Specifically, if the user's walking route is straight, the main direction of his motion trajectory can be regarded as his forward direction, that is, the stride length direction. All these calculations are implemented by custom MATLAB code.

[0084] Fourth, at each heel strike, calculate the center of pressure (CoP) at the heel, and at the metatarsal bones (CoP') at the push-off. The angle between the line connecting the two center of pressure and the direction of travel is the foot deflection angle. The specific steps are as follows:

[0085] Calculation of the center of pressure (CoP) when the heel strikes: Use the plantar pressure sensor data to identify the pressure distribution when the heel strikes, and calculate the position of the center of pressure at this time based on the pressure distribution map.

[0086] Calculation of the center of pressure (CoP') at the metatarsal bones during push-off: Also using the plantar pressure sensor data, the pressure distribution during push-off is identified, and the position of the center of pressure at this time is calculated based on the pressure distribution diagram.

[0087] Calculation of foot deflection angle (θ): The foot deflection angle is obtained by calculating the angle between the line between CoP and CoP' and the forward direction, such as Figure 2 The formula is as follows:

[0088]

[0089] Where θ is the foot deflection angle, CoP x and CoP y Respectively represent the x and y coordinates of the center of pressure at the heel, CoP' x and CoP' y Respectively represent the x and y coordinates of the center of pressure at the metatarsal bones.

[0090] Finally, by combining the plantar pressure distribution, foot deflection angle and foot motion trajectory, the foot position during gait can be reproduced. Thus, a large number of gait parameter data can be calculated, including step length, step width, step speed, stance phase time, plantar pressure distribution, center of pressure (COP) curve, etc. The obtained bipedal posture is as follows Figure 3 shown.

[0091] To validate the effectiveness of the system, the spatiotemporal parameter estimation was compared with the gold standard Vicon optical motion capture system. Experimental protocol for the comparison and validation of the optical motion capture lab with the Lab-in-Shoe smart shoe system. Two young healthy males (age: 24.5±0.5 years; height: 176.0±2cm) participated in the study. The Vicon camera was calibrated and the system was prepared for data acquisition in an 8-meter-long motion capture lab. Subsequently, the IMU, insole-based plantar pressure mapping sensors, and markers were installed on the shoes, and the participants were asked to walk straight within the capture volume (about 4 meters). During this period, data from Vicon and the "Lab-in-Shoe" were collected simultaneously. At the beginning of the experiment, the participants were asked to stomp their right foot to achieve event synchronization between the Vicon data and the "Lab-in-Shoe" data. The subjects repeated the experiment three times at three different walking speeds: comfortable (1.1±0.07m / s), slow (0.68±0.05m / s), and fast (1.4±0.13m / s). The validity of the Lab-in-shoe gait detection system was evaluated by Bland-Altman 95% limits of agreement with the gold standard optical motion capture system (Vicon). The Bland-Altman plots for all results (n=67) showed very small deviations (0.03m), with a relative error of about 3% for stride length. Most of the Lab-in-shoe measurements were within the 95% confidence interval, indicating good validity. Reliability was assessed by intraclass correlation (ICC 2,k). The stride length of the Lab-in-shoe corresponded to the motion capture measurements and was plotted together with the intraclass correlation (ICC) and the corresponding linear fit. The ICC values ​​for stride length were 0.99 (n=22) at low speeds, 0.984 (n=28) at comfortable speeds, and 0.961 (n=17) at faster speeds. This shows that the system's estimation of gait parameters is quite consistent with the motion capture measurements, and there is little effect on the accuracy of gait parameter acquisition regardless of walking speed.

[0092] The smart shoes of the present invention can realize continuous monitoring and analysis of gait data, thereby making it possible to collect, analyze and predict early diseases of large-scale clinical gait data. In the future, the system will also be applied to different foot and ankle clinical scenarios, including chronic ankle instability, ankle osteoarthritis, flat feet and equinus deformity, and establish a large-scale database. This will promote the application of quantitative objective gait analysis methods in foot and ankle clinical practice, and ultimately achieve rapid diagnosis and evaluation and precise rehabilitation treatment of foot and ankle patients through wearable devices. In addition, the collected big data will also provide important support for foot and ankle pathology research, and the design and development of prostheses and functional assistive devices.

[0093] The above describes the gait analysis method based on smart shoes in the embodiment of the present invention. The following describes the gait analysis system based on smart shoes in the embodiment of the present invention. Figure 2 , the first embodiment of the gait analysis device based on smart shoes in the embodiment of the present invention includes:

[0094] A gait phase division unit, used to obtain pressure distribution data captured by a plantar pressure sensor, divide the gait phase according to a time pattern, and identify the gait phase, wherein the identified gait phase is obtained by foot contact detection and toe-off detection, and the gait phase includes a support phase and a swing phase;

[0095] An acceleration conversion unit is used to obtain the three-dimensional acceleration, angular velocity and magnetic field data of the inertial measurement unit, convert the three-dimensional acceleration data from the IMU coordinate system to the earth coordinate system, and obtain the three-dimensional acceleration data based on the earth coordinate system;

[0096] A zero speed update unit is used to obtain initial speed data by integrating the three-dimensional acceleration data based on the earth coordinate system, determine the zero speed moment in the gait by combining the pressure pattern of the plantar pressure distribution data, and then apply the zero speed update algorithm to correct the error accumulation caused by the inertial sensor noise and signal drift to obtain the corrected speed data;

[0097] The motion trajectory calculation unit is used to obtain the motion trajectory of the foot by integrating the corrected speed data.

[0098] The stride and step length decoupling unit is used to obtain the vectors of the stride length direction and the step width direction during walking by applying the principal component analysis algorithm to the foot motion trajectory, and then project the foot motion trajectory along the stride length direction vector and the step width direction vector respectively to complete the decoupling of the stride length and step width data and obtain the stride length and step width parameters in the gait.

[0099] The visualization unit combines and visualizes the plantar pressure distribution data cloud map with the foot movement trajectory to complete the visualization reproduction of the foot posture during the gait process.

[0100] The structure of an electronic device provided by an embodiment of the present invention may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) (for example, one or more processors) and memories, and one or more storage media for storing applications or data (for example, one or more mass storage devices). Among them, the memories and storage media may be short-term storage or permanent storage. The program stored in the storage medium may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the electronic device. Furthermore, the processor may be configured to communicate with the storage medium and execute a series of instruction operations in the storage medium on the electronic device.

[0101] The electronic device may also include one or more power supplies, one or more wired or wireless network interfaces, one or more input and output interfaces, and / or one or more operating systems, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will appreciate that the electronic device structure does not constitute a limitation on the electronic device, and may include more or less components than the aforementioned, or combine certain components, or arrange the components differently.

[0102] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of a gait analysis method based on smart shoes.

[0103] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device, or unit can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0104] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0105] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A gait analysis method based on smart shoes, characterized in that: The following steps are involved: Acquire pressure distribution data captured by a plantar pressure sensor, divide gait phases according to pressure patterns, and identify gait phases, wherein the identified gait phases are obtained through foot contact detection and toe-off detection, and the gait phases include a stance phase and a swing phase; Obtain the three-dimensional acceleration, angular velocity and magnetic field data of the inertial measurement unit, convert the three-dimensional acceleration data from the IMU coordinate system to the earth coordinate system, and obtain the three-dimensional acceleration data based on the earth coordinate system; The initial velocity data is obtained by integrating the three-dimensional acceleration data based on the earth coordinate system, and the zero velocity moment in the gait is determined by combining the pressure pattern of the plantar pressure distribution data. Then, the zero velocity update algorithm is applied to correct the error accumulation caused by the inertial sensor noise and signal drift, and the corrected velocity data is obtained. The movement trajectory of the foot is obtained by performing a second integration calculation on the corrected speed data; Through the principal component analysis algorithm, the step length and step width displacement in the foot motion trajectory are decoupled to obtain the step length and step width parameters; By combining the plantar pressure distribution data cloud map with the foot motion trajectory and visualizing them, the visual reproduction of the foot posture during the gait process is completed.

2. The gait analysis method based on smart shoes according to claim 1, characterized in that: The gait analysis method further comprises a foot deviation angle estimation step: According to the movement trajectory of the foot, the pressure center point at the heel is calculated each time the heel touches the ground, and the pressure center point at the metatarsal is calculated when pushing off. The angle between the line connecting the two pressure center points and the forward direction is the foot deviation angle.

3. The gait analysis method based on smart shoes according to claim 1, characterized in that: The foot contact detection method is: The moment when the foot touches the ground is detected by monitoring the vertical ground reaction force (vGRF) from the pressure sensor. When the vGRF exceeds a predetermined threshold, it is recognized that the foot has touched the ground. The formula is as follows: Among them, vGRF i 、vGRF i-1 is the plantar pressure, vGRF threshold is the sensor pressure threshold.

4. The gait analysis method based on smart shoes according to claim 3, characterized in that: The toe-off detection method is as follows: When the vGRF is lower than a predetermined threshold, a foot-off event is detected, indicating that the foot is leaving the ground; Through foot contact detection and toe-off detection, the various phases of the gait cycle are identified, thereby performing gait phase segmentation.

5. The gait analysis method based on smart shoes according to claim 4, characterized in that: The method for calculating the pressure center point CoP when the heel touches the ground is as follows: using the plantar pressure sensor data, identifying the pressure distribution when the heel touches the ground, and calculating the position of the pressure center point at this time according to the pressure distribution diagram; The method for calculating the pressure center point CoP' at the metatarsal during push-off is: also using the plantar pressure sensor data, identifying the pressure distribution during push-off, and calculating the pressure center point position at this time according to the pressure distribution diagram.

6. The gait analysis method based on smart shoes according to claim 5, characterized in that: The calculation method of the foot deflection angle is: The foot deflection angle is obtained by calculating the angle between the line between CoP and CoP' and the forward direction. The formula is as follows: Where θ is the foot deflection angle, CoP x and CoP y denote the x and y coordinates of the center of pressure at the heel, CoP′ x and CoP′ y Respectively represent the x and y coordinates of the center of pressure at the metatarsal bones.

7. The gait analysis method based on smart shoes according to claim 1, characterized in that: The three-dimensional acceleration data is converted from the IMU coordinate system to the earth coordinate system as follows: The acceleration vector a in the IMU coordinate system IMU The acceleration vector a converted to the Earth coordinate system earth The formula is: a earth =R·a IMU Among them, R is the rotation matrix, and the calculation formula of R is: R=R z (W)R y (i)R x (F) Among them, R x (Φ), R y (θ) and R z (Ψ) are the rotation matrices around the x-axis, y-axis, and z-axis, respectively, and can be expressed as:

8. A gait analysis system based on smart shoes, characterized in that: The system comprises: A gait phase division unit, used to obtain pressure distribution data captured by a plantar pressure sensor, divide the gait phase according to the pressure pattern, and identify the gait phase, wherein the identified gait phase is obtained by foot contact detection and toe-off detection, and the gait phase includes a support phase and a swing phase; An acceleration conversion unit is used to obtain the three-dimensional acceleration, angular velocity and magnetic field data of the inertial measurement unit, convert the three-dimensional acceleration data from the IMU coordinate system to the earth coordinate system, and obtain the three-dimensional acceleration data based on the earth coordinate system; A zero speed update unit is used to obtain initial speed data by integrating the three-dimensional acceleration data based on the earth coordinate system, determine the zero speed moment in the gait by combining the pressure pattern of the plantar pressure distribution data, and then apply the zero speed update algorithm to correct the error accumulation caused by the inertial sensor noise and signal drift to obtain the corrected speed data; A motion trajectory calculation unit, used for obtaining the motion trajectory of the foot by integrating the corrected speed data; A stride length and step length decoupling unit is used to obtain the vectors of the stride length direction and the step width direction during walking by applying the principal component analysis algorithm to the foot motion trajectory, and then project the foot motion trajectory along the stride length direction vector and the step width direction vector respectively to complete the decoupling of the stride length and step width data, and obtain the stride length and step width parameters in the gait; The visualization unit combines and visualizes the plantar pressure distribution data cloud map with the foot movement trajectory to complete the visualization reproduction of the foot posture during the gait process.

9. An electronic device, comprising a memory and at least one processor, wherein instructions are stored in the memory; The at least one processor calls the instructions in the memory to enable the electronic device to execute the various steps of the gait analysis method based on smart shoes as described in any one of claims 1-7.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the various steps of the gait analysis method based on smart shoes as described in any one of claims 1 to 7 are implemented.

Images