A pedestrian inertial navigation method based on action recognition

Abstract

The present invention belongs to the field of pedestrian navigation and positioning technology, and relates to a pedestrian inertial navigation method based on motion recognition. The method relies on wearable devices to collect IMU data and muscle electrical data; in a stationary state, the Euler angle is calculated based on the IMU data and the coordinate rotation matrix is ​​obtained, the acceleration in the carrier coordinate system is converted to the navigation coordinate system, and the speed information is obtained after integration; after preprocessing and feature extraction of the muscle electrical data, an SVM model based on statistics and motion correction algorithms is used to identify the motion state of the human body in a mixed motion mode, and a motion recognition result is obtained; the motion recognition result is used to adaptively adjust the threshold detection of the zero-speed interval, and finally, the zero speed is corrected in the zero-speed interval using an EKF-based speed correction method and the corrected speed is integrated to obtain position information. The method can achieve higher positioning accuracy, smaller positioning error, better robustness and more accurate trajectory drawing in a mixed motion mode.

Description

Technical Field

[0001] The present invention belongs to the technical field of pedestrian navigation and positioning, and relates to a pedestrian inertial navigation method based on motion recognition. Background Art

[0002] With the development of technologies such as wireless communications and sensors, the demand for navigation and positioning is increasing. Positioning systems are now ubiquitous in a wide range of everyday applications. This familiarity is largely due to the Global Positioning System (GPS). While this technology provides good positioning results in outdoor applications, its performance in indoor applications is unsatisfactory due to weak GPS signals that cannot penetrate building walls and the presence of multipath. This demonstrates the significant research significance of achieving high-precision indoor pedestrian navigation. Furthermore, its application scenarios are extensive, such as providing indoor navigation services within large buildings, tracking the location of items in logistics systems, and monitoring the location of patients in hospitals. In particular, indoor positioning can be used for security monitoring and emergency rescue within buildings and in underground parking lots, improving safety and efficiency. Therefore, highly reliable and high-precision pedestrian navigation and indoor positioning technologies are of vital research significance and application value.

[0003] Currently, there's a challenge in pedestrian inertial navigation based on zero-speed correction: fixed thresholds within zero-speed correction algorithms make it difficult to accurately detect zero-speed intervals in mixed motion patterns. Detecting zero-speed intervals is even more challenging in situations like running and jumping, where the foot's contact time with the ground is brief. Beyond being stationary, human motion can be broadly categorized into general motion, competitive motion, and movement. General motion primarily includes walking, running, walking backward, stepping to the right, stepping to the left, turning right, turning left, ascending hills / stairs, descending hills / stairs, standing, sitting, and lying down. Competitive motion primarily includes running, jumping, crawling, climbing, and dodging. Movement primarily includes escalators, elevators, cycling, cars, and trains. While most people engage in everyday motion, specialized personnel like soldiers and firefighters employ a variety of motion patterns, including crawling, stepping, climbing, and dodging. Therefore, it's necessary to conduct more precise perception research on human motion patterns and integrate it with navigation and positioning technologies to improve the accuracy and efficiency of pedestrian navigation and positioning.

[0004] In recent years, with the rapid development of technologies such as system integration, microsensors, the Internet of Things, 5G, and artificial intelligence, research and application in wearable devices and related fields have become increasingly widespread. Compact and lightweight, wearable devices possess the ability to continuously sense, collect, and upload information and physiological data. They have been widely used in fields such as virtual reality, healthcare, health monitoring, and physical training. With the advancement of microelectromechanical (MEMS) technology, the integration of inertial measurement units (IMUs) has gradually increased, and their reduced size and weight have made them easier to wear. Researchers are leveraging kinematic information collected by IMUs to achieve motion recognition and parameter prediction. In addition to focusing on whole-body motion capture, research is also focused on localized motion capture and lower limb motion parameter estimation. Surface electromyography (sEMG) signals are weak bioelectric currents that are highly real-time and less susceptible to environmental influences. Signals collected by sEMG sensors provide a direct, non-invasive data source for motion recognition and motion parameter estimation. Processing can extract key information such as muscle contraction state, force, and timing.

[0005] In the lower limb movement recognition task, the correlation between the topological characteristics of the device and the task is taken into consideration, and feature extraction and screening methods are combined. To address the problem of low recognition rate of the traditional support vector machine (SVM) model, an SVM model based on statistical analysis and motion correction algorithm is used to identify the lower limb movement state in mixed motion modes. This model is then applied to the pedestrian inertial navigation method. According to the recognition results, the detection threshold of the zero-speed interval is adaptively adjusted to reduce the missed detection and false detection rates in the zero-speed interval, thereby improving the positioning accuracy.

[0006] Therefore, to address the above-mentioned issues, this application combines zero-speed correction with motion pattern recognition to assist pedestrian navigation, further improving the performance of pedestrian inertial navigation methods under mixed motion modes. Specifically, the proposed motion pattern recognition algorithm is used to identify support vector machines (SVMs), a machine learning method for classification problems that aims to achieve linear classification by defining the maximum margin in feature space. Summary of the Invention

[0007] The purpose of the present invention is to solve the problem that zero-speed interval detection based on a fixed threshold in a hybrid motion mode has interval omission and false detection, which leads to reduced positioning accuracy. A pedestrian inertial navigation method based on motion recognition is proposed, which is adapted to different pedestrian motion modes and relies on wearable devices to collect IMU data and muscle electrical data; in a static state, the Euler angle is calculated based on the IMU data and the coordinate rotation matrix is ​​obtained, the acceleration in the carrier coordinate system is converted to the navigation coordinate system, and the speed information is obtained after integration; the muscle electrical data is preprocessed and feature extracted (the extracted features include time domain features: mean absolute value (MAV), root mean square value (RMS), variance (VARE), integrated electromyogram (IEMG), wavelength (WL) and Willison amplitude (Willison Abstract: A novel method for positioning human body in mixed motion mode is proposed. After the human body is trained on the basis of the velocity amplitude (WA), a support vector machine (SVM) model based on statistics and motion correction algorithms is used to identify the motion state of the human body in mixed motion mode, thereby obtaining motion recognition results. The motion recognition results are used to adaptively adjust the threshold detection in the zero-speed interval. Finally, a velocity correction method based on an extended Kalman filter (EKF) is used within the zero-speed interval to correct the zero speed and integrate the corrected velocity to obtain position information. The method can achieve high positioning accuracy, small positioning error, good robustness and more accurate trajectory drawing in mixed motion mode.

[0008] In order to achieve the above object, the present invention adopts the following technical solutions:

[0009] A pedestrian inertial navigation method based on motion recognition includes the following steps:

[0010] S1, collect sEMG signals and IMU data through wearable devices;

[0011] S2, preprocessing the sEMG signal to obtain preprocessed sEMG data;

[0012] At the same time, in a stationary state, the IMU data is used to calculate the Euler angle and obtain the coordinate rotation matrix, converting the acceleration in the carrier coordinate system to the navigation coordinate system, and obtaining the velocity information after integration;

[0013] S3, extracting the time domain features, time-frequency features, and time-advance features of the preprocessed sEMG data and combining them to obtain a feature data vector;

[0014] S4, repeat S1 to S3 multiple times to collect and obtain multiple sets of feature data vectors of different subjects in different motion states, and then divide these feature data vectors into training sets and test sets in proportion;

[0015] S5. Perform feature screening on the feature data of the training set and update the data set;

[0016] S6. Construct and train an SVM model based on statistics and motion correction, specifically: traverse the training set and run the SVM model to identify different motion patterns, traverse and obtain the Gaussian kernel bandwidth and penalty coefficient corresponding to the motion pattern with the highest recognition accuracy; statistically analyze the recognition results of the SVM model within a certain time interval, select the motion state recognition result with the mode being the time interval to update the SVM model, and obtain a statistical analysis SVM model; further correct the motion pattern of the previous window by the current estimated motion pattern and update the hyperparameters of the statistical analysis SVM model based on this recognition result, and obtain an SVM model based on statistics and motion correction;

[0017] S7, adjusting the zero-speed detection threshold of the corresponding motion mode according to the SVM model based on statistics and motion correction of the test set and the motion mode recognition result;

[0018] S8. Perform zero-speed detection based on the zero-speed detection threshold of the motion mode and the speed information obtained in S2. If the speed is detected to be zero, perform zero-speed correction, and then integrate the corrected speed to obtain position information. If the speed is detected to be non-zero, do not perform zero-speed correction, and directly integrate the speed information obtained in S2 to obtain position information.

[0019] The wearable device described in S1 includes electrodes and a sensor group; the sensor group includes an accelerometer, a gyroscope and a magnetometer; the IMU data is obtained by collecting human motion information through the accelerometer, gyroscope and magnetometer; the human motion information includes but is not limited to acceleration information, velocity information and coordinate information.

[0020] The velocity information is obtained by calculating the Euler angle and obtaining the coordinate rotation matrix in a stationary state, converting the acceleration in the carrier coordinate system to the navigation coordinate system, and then integrating it; the sEMG signal is multi-channel surface electromyography information of the lower limb muscle groups collected based on electrodes in the wearable device; the number of electrodes is greater than 2 and less than 30.

[0021] The sEMG signal preprocessing step S2 specifically includes the following sub-steps:

[0022] S21, filtering out high-frequency noise of the sEMG signal by low-pass filtering to obtain a low-pass filtered sEMG signal;

[0023] S22, performing a first-stage amplification on the low-pass filtered sEMG signal to obtain a first-stage amplified sEMG signal;

[0024] S23, performing high-pass filtering on the first-stage amplified sEMG signal to obtain a high-pass filtered sEMG signal;

[0025] S24, performing secondary amplification on the high-pass filtered sEMG signal to obtain a secondary amplified sEMG signal;

[0026] S25. Convert the secondary amplified sEMG signal into pre-processed sEMG data via an analog-to-digital converter.

[0027] The cutoff frequency of the low-pass filter described in S21 is greater than 10Hz and less than 200Hz; the amplification factor of the first-stage amplification described in S22 is greater than or equal to 5 and less than or equal to 100 when implemented; the cutoff frequency of the high-pass filter described in S23 is greater than or equal to 100Hz and less than or equal to 200Hz, and the high-pass filter can remove low-frequency noise mainly composed of drift and motion artifacts; the amplification factor of the second-stage amplification described in S24 is greater than or equal to 10 and less than or equal to 200 when implemented.

[0028] The combination of S3 includes but is not limited to addition, subtraction, series connection and parallel connection; the time domain features, time-frequency features and time-advance features are used to train the SVM model based on statistics and motion correction; the time domain features include but are not limited to MAV, RMS, VARE, IEMG, WL and WA; the time-frequency features include but are not limited to FFT, STFT and wavelet decomposition; the wavelet basis used in the wavelet decomposition includes Haar wavelet basis, dbN wavelet basis, symN or Bior wavelet basis; the number of layers of the wavelet decomposition is greater than or equal to 3 layers and less than or equal to 10 layers in specific implementation; the time-advance feature is extracted based on the advance time window; the value range of the advance time window is greater than or equal to 10ms and less than or equal to 300ms.

[0029] The specific extraction process of the time-advanced feature is as follows: 1) determining the advance time window; 2) extending the time length of the advance time window from the current time point forward, and adding a fixed time window; 3) extracting the features of the total time length data within the advance time window and the fixed time window; 4) obtaining the features of the total time length data within the advance time window and the fixed time window in sequence with the time step as the interval.

[0030] The fixed time window has a value range of greater than or equal to 180 ms and less than or equal to 220 ms; the time step has a value range of greater than or equal to 10 ms and less than or equal to 50 ms.

[0031] The ratio of the training set and the test set in S4 ranges from 6:4 to 9:1; the different motion states include but are not limited to going up stairs, going down stairs, squatting, standing up, standing and walking at a constant speed.

[0032] The value range of the certain time interval in S6 is: 100ms to 800ms;

[0033] S7 is specifically as follows: S71, inputting the test set into the SVM model based on statistics and action correction to perform pattern recognition;

[0034] S72, drawing a T curve and selecting zero-speed detection thresholds for various motion modes based on the T curve;

[0035] S73 , identifying various motion modes and adjusting the zero-speed detection threshold corresponding to the motion mode according to the motion mode identification result.

[0036] Beneficial effects

[0037] The pedestrian inertial navigation method based on motion recognition proposed in this invention has the following advantages compared with the existing method based on fixed threshold:

[0038] 1. This method considers that the application of complex neural network models to pedestrian inertial navigation increases algorithm complexity and the traditional SVM method has low accuracy in identifying motion states. This method combines statistical analysis and motion correction algorithms to optimize the motion classification results of the SVM model under mixed motion conditions, thereby improving the accuracy of motion recognition under mixed motion conditions and providing conditions for the application of pedestrian inertial navigation methods in complex motion scenes.

[0039] 2. The method selects the zero-speed detection threshold for different motion states according to the T-curve characteristics of different motion states, and sets the corresponding zero-speed detection threshold according to the motion recognition results, thereby improving the detection rate of the zero-speed interval. After correcting the speed within the zero-speed interval detected by the adaptive threshold, a more accurate motion trajectory is obtained, reducing the positioning error. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a flow chart of a pedestrian inertial navigation method based on motion recognition according to the present invention;

[0041] Figure 2 A schematic diagram of a wearable device used in a pedestrian inertial navigation method based on motion recognition according to the present invention;

[0042] Figure 3 Schematic diagram of wavelet decomposition;

[0043] Figure 4 is the ranking of feature weights;

[0044] Figure 5Schematic diagram of motion state correction method;

[0045] Figure 6 This is the zero-speed interval discrimination result of the existing technology with a fixed threshold;

[0046] Figure 7 This is the zero-speed interval discrimination result based on the adaptive threshold of the present invention;

[0047] Figure 8 This is the zero-speed correction result based on a fixed threshold in the existing technology;

[0048] Figure 9 It is the zero-speed correction result based on the adaptive threshold of the present invention;

[0049] Figure 10 are the motion trajectories and true values ​​of the fixed and adaptive thresholds. DETAILED DESCRIPTION

[0050] The following further illustrates and describes in detail a pedestrian inertial navigation method based on motion recognition according to the present invention in conjunction with the accompanying drawings and embodiments.

[0051] Example 1

[0052] The present invention proposes a pedestrian inertial navigation method based on motion recognition, the process is as follows: Figure 1 As shown in the following example, the specific implementation is as follows: First, wear the wearable device to the feet and thighs to collect IMU data and muscle electrical data, as shown in the following example: Figure 2 As shown in the figure; secondly, in a stationary state, IMU data is used to calculate Euler angles and obtain the coordinate rotation matrix. The acceleration in the carrier coordinate system is converted to the navigation coordinate system, and the velocity information is obtained after integration. After preprocessing and feature extraction of the muscle electrical data, a support vector machine (SVM) model based on statistics and motion correction algorithms is used to identify the human body's motion state in mixed motion modes, obtaining motion recognition results. The motion recognition results are then applied to adaptively adjust the detection threshold in the zero-speed interval. Finally, an EKF-based velocity correction method is used within the zero-speed interval to perform zero-speed correction. The corrected velocity is then integrated to obtain position information. Ultimately, the navigation system achieves high positioning accuracy, small positioning error, good robustness, and relatively accurate trajectory drawing in mixed motion modes.

[0053] The method involves wearing a wearable device to the thigh to collect sEMG data and IMU data, as specifically embodied in S1 of the invention content, preprocessing the collected sEMG data and IMU data, and after calculating the Euler angle and obtaining the coordinate rotation matrix in a stationary state, converting the acceleration in the carrier coordinate system to the navigation coordinate system, integrating the acceleration to obtain velocity information, as specifically embodied in S2 of the invention content, performing feature extraction on the preprocessed sEMG data and IMU data, as specifically embodied in S3 of the invention content, obtaining multiple groups of feature data vectors under different motion states of different subjects, and then dividing these feature data vectors into training sets and test sets in proportion, as specifically embodied in S4 of the invention content, calculating feature weights of the extracted features using the NCFS algorithm for feature screening. , specifically embodied in S5 of the invention content, constructing a statistical analysis algorithm and a method for motion correction based on adjacent window gait constraints, and integrating them with the SVM machine learning model, thereby constructing an SVM model based on statistics and motion correction algorithms to identify the motion state of the human body in the mixed motion mode, specifically embodied in S6 of the invention content, and then constructing an adaptive threshold adjustment algorithm, applying the motion recognition result to adaptively adjust the detection threshold of the zero-speed interval, specifically embodied in S7 of the invention content, and then performing zero-speed detection to determine whether it is in the zero-speed interval, correcting the zero speed in the zero-speed interval, and integrating the corrected speed to obtain position information, and directly integrating the non-zero speed that is not in the zero-speed interval to obtain position information, specifically embodied in S8 of the invention content, and finally realizing pedestrian inertial navigation. The present invention realizes that the navigation system has high positioning accuracy, small positioning error, good robustness, and draws more accurate trajectories in the mixed motion mode.

[0054] In the implementation of the method described herein, a closed rectangular path test was conducted. The path for data collection based on the wearable device was a closed rectangle with a width of 26 meters and a length of 18 meters. The four corners of the rectangular path were in a standing position, the wide side was in a running position, and the long side was in a walking position. The test data collection time for this experiment was approximately 70 seconds.

[0055] The specific implementation includes the following steps:

[0056] S1, collect sEMG signals and IMU data through wearable devices;

[0057] The wearable device includes electrodes and a sensor group; the sensor group includes an accelerometer, a gyroscope, and a magnetometer; the wearable device is specifically implemented as a leg ring and an IMU, and data is collected by wearing the leg ring on the thigh and the IMU on the shoelaces of the foot. The initial position of the leg ring needs to be aligned to ensure that the center of the first sEMG electrode of the leg ring is aligned with the center of the knee, and then the leg ring can be worn at the position with the richest muscles on the thigh. The specific wearing diagrams are shown in Figures (2a) and (2b);

[0058] The sEMG signal is multi-channel surface electromyography information of lower limb muscles collected by electrodes in the wearable device;

[0059] The IMU data is obtained by collecting human motion information from an accelerometer, a gyroscope, and a magnetometer; the human motion information is specifically implemented as acceleration information, velocity information, and coordinate information;

[0060] The velocity information is obtained by calculating the Euler angles in a stationary state and obtaining a coordinate rotation matrix, converting the acceleration in the carrier coordinate system to the navigation coordinate system, and then integrating the calculated acceleration.

[0061] The number of electrodes is 16 in a specific implementation. For subjects with a height range of 150 cm to 190 cm and a weight range of 100 to 200 catties, a leg ring with 16 channels or more is used, and a specific wearing diagram is shown in Figure (2c); for subjects with a weight of less than 100 catties and a height of less than 150 cm, a leg ring with 12 channels or less is used, and a specific wearing diagram is shown in Figure (2d);

[0062] S2, preprocessing the sEMG signal to obtain preprocessed sEMG data, specifically including the following sub-steps;

[0063] S21, filtering out high-frequency noise of the sEMG signal by low-pass filtering to obtain a low-pass filtered sEMG signal;

[0064] The cutoff frequency of the low-pass filter is specifically implemented as 10 Hz;

[0065] S22, performing a first-stage amplification on the low-pass filtered sEMG signal to obtain a first-stage amplified sEMG signal;

[0066] The magnification of the first-level amplification is 10 in practice;

[0067] S23, performing high-pass filtering on the first-stage amplified sEMG signal to obtain a high-pass filtered sEMG signal;

[0068] The cutoff frequency of the high-pass filter is 20 Hz when specifically implemented;

[0069] S24, performing secondary amplification on the high-pass filtered sEMG signal to obtain a secondary amplified sEMG signal;

[0070] The magnification of the secondary amplification is 20 in the specific implementation;

[0071] S25, converting the secondary amplified sEMG signal into pre-processed sEMG data via an analog-to-digital converter;

[0072] S3, extracting the time domain features, time-frequency features, and time-advance features of the preprocessed sEMG data and combining them to obtain a feature data vector;

[0073] The combination is specifically implemented in series;

[0074] The time domain features, time-frequency features and time-advance features are used to train a SVM model based on statistics and motion correction;

[0075] The time domain features are specifically implemented as MAV, RMS, VARE, IEMG, WL and WA;

[0076] The MAV, through Calculate, where x i represents the i-th sEMG signal sample point, K is the total length of the signal in the time window; the RMS is obtained by Calculate; the VARE, by Calculate, where Represents the average value of K sEMG signal sample points; the IEMG, through Calculate; the WL, by Calculate, where x i+1 represents the i+1th sEMG signal sample point; the WA is obtained by Calculate, where th is the threshold;

[0077] The time-frequency features include but are not limited to FFT, STFT and wavelet decomposition; in specific implementation, wavelet decomposition is performed on MAV, RMS and WL features, and the wavelet basis used in the wavelet decomposition is db7 wavelet basis; the number of layers of the wavelet decomposition is 3 layers in specific implementation; the specific decomposition diagram is as follows Figure 3 As shown. Among them, cA 1 、cA 2 and cA 3 Represent the approximate components of each layer of wavelet decomposition, cD 1 、cD 2 and cD 3 They represent the detail components of each layer after decomposition respectively. The present invention extracts the three detail components obtained by decomposition and the approximate component of the last layer.

[0078] The time-advance feature is extracted based on the advance time window; the advance time window is 200ms in specific implementation;

[0079] The specific extraction process of the time-advanced feature is as follows: 1) determining the advance time window; 2) extending the time length of the advance time window from the current time point forward, and adding a fixed time window; 3) extracting the features of the total time length data within the advance time window and the fixed time window; 4) obtaining the features of the total time length data within the advance time window and the fixed time window in sequence with the time step as the interval.

[0080] The fixed time window is 200ms when implemented; the time step is 20ms when implemented;

[0081] When the present invention is implemented, all the features extracted are shown in Table 1, where the features prefixed with app are the features of the last layer of approximate components extracted by wavelet decomposition, the features prefixed with cd1, cd2, and cd3 are the features of the first, second, and third level detail components extracted by wavelet decomposition, respectively, and the features prefixed with ad represent the features extracted based on the time advance window;

[0082] Table 1 All features extracted in this example

[0083]

[0084]

[0085] S4, repeat S1 to S3 multiple times to collect and obtain multiple sets of feature data vectors of different subjects in different motion states, and then divide these feature data vectors into training sets and test sets in proportion;

[0086] The training set and the test set are divided into a ratio of 6:4 when implemented;

[0087] The different motion states include walking up stairs, walking down stairs, squatting, standing up, standing and walking at a constant speed;

[0088] In the specific implementation of S4, in the stair climbing and descending experiments, the data collection duration was 10 seconds. The subjects first stood for 2 seconds and then went up or down the stairs for the next 8 seconds. For squatting and standing up, the data collection time was 8 seconds. The subjects stood for the first 2 seconds, squatted for the next 2-4 seconds, remained squatting for 4-6 seconds, and finally stood up within 6-8 seconds. The data collection of the walking state lasted for 55 seconds. The subjects stood for the first 2 seconds and walked at a constant speed for the next 53 seconds.

[0089] S5. Perform feature screening on the feature data of the training set and update the data set;

[0090] The feature screening uses the NCFS algorithm to find a weighted vector that maximizes the similarity between samples of the same type and minimizes the similarity between samples of different types. Specifically:

[0091] S51. Calculate two samples x i with x j The weighted distance of

[0092] The two samples x i with x j The weighted distance, denoted as D w (x i ,x j ),pass Calculate, where w l is the weight of the l-th dimension feature, x il Represents x i The lth dimension feature, x jl Represents x j The lth dimension feature, d is the feature vector x i Dimensions;

[0093] S52. Query sample x i Select a sample x in the space j As the probability of the reference point; the probability reflects the relative position relationship of the sample in the feature space;

[0094] The sample x i Select a sample x in the space j As the probability of the reference point, denoted as p ij ,pass Calculate, where k(z) = exp(-z / σ) is the kernel function and σ is the kernel width;

[0095] The reference points refer to other samples used to calculate the distance between samples;

[0096] S53. Calculate sample x i Probability of correct classification;

[0097] The sample x i The probability of correct classification is denoted as p i ,pass Calculate, where y i is the sample label, y i ∈{1,2,3,···,C};

[0098] S54. Calculate the average correct classification probability of all samples, that is, the classification accuracy;

[0099] The accuracy of the classification, denoted as ε(w), is obtained by Calculate, where N is the number of samples in the training set;

[0100] S55. In order to alleviate overfitting, a regularization term is introduced to obtain the objective function;

[0101] The objective function, denoted as ε(w), is obtained by Calculate, where λ>0 is the regularization parameter, which is used to control the strength of regularization and can be adjusted by cross-validation;

[0102] S56. Derivate the above objective function ε(w) and update the feature weight w l ;

[0103] The result after derivation is recorded as pass:

[0104]

[0105] Calculate and get the gradient update equation of NCFS algorithm;

[0106] The updated feature weight w l ,pass Calculate, where η is the learning rate;

[0107] S57, calculating feature weights according to the NCFS algorithm;

[0108] The feature weight in the NCFS algorithm is calculated based on the training set. The feature weight value is denoted as w f ,pass Calculate, where K is the number of IMU and sEMG channels, w fi and w adfi are the weights of the features of each channel and the corresponding time-advanced features respectively;

[0109] The present invention uses the NCFS algorithm to obtain the weight values ​​of the features VARE, IEMG, RMS, WL, MAV, WA, DB7-MAV, DB7-RMS and DB7-WL, as shown in the following example: Figure 4 shown. Figure 4 Sort the weight values ​​of each feature from large to small. The weight values ​​from high to low are WL, RMS, cd 3 -MAV, VARE, IEMG, MAV, app-WL, cd 1 -MAV, CD 1 -RMS, cd 1 -WL,app-RMS,cd 3 -RMS, cd 3 -WL, WA, cd 2 -MAV, CD 2 -RMS, app-MAV, cd 2-WL;

[0110] S58. Take the top five weighted features and their time-advanced features as the retained feature data to update the training set, validation set, and test set. Specifically for this embodiment, all retained features are shown in Table 2:

[0111] Table 2 Summary of features retained after feature screening in this example

[0112]

[0113] S6. Build and train an SVM model based on statistics and motion correction, specifically:

[0114] S61, traverse the training set and run the SVM model to identify different action patterns, traverse and obtain the Gaussian kernel bandwidth and penalty coefficient corresponding to the action pattern with the highest recognition accuracy;

[0115] S62, statistically analyzing the recognition results of the SVM model within a certain time interval, and selecting the mode as the motion state recognition result of the time interval; the time interval is specifically implemented as 0.5s;

[0116] S63, further correcting the motion pattern of the previous window by the current estimated motion pattern and updating the hyperparameters of the SVM model based on the recognition result, to obtain an SVM model based on statistics and motion correction, specifically: assuming that the motion types estimated by four consecutive adjacent windows are A, B, C and D respectively, when A=C and B≠C, it means that the motion category B is misjudged, then the motion category of B is corrected to the motion category of A and C. When A=B and B≠C and C≠D, it means that the motion category C is misjudged, then the motion category of C is corrected to the motion category of A and B, as shown in the following example: Figure 5 shown.

[0117] S7, adjusting the zero-speed detection threshold of the corresponding motion mode according to the SVM model based on statistics and motion correction of the test set and the motion mode recognition result, specifically including the following sub-steps:

[0118] S71, inputting the test set into the SVM model based on statistics and action correction to perform pattern recognition;

[0119] S72, drawing a T curve and selecting zero-speed detection thresholds for various motion modes based on the T curve;

[0120] The T curve, through Calculate, where ω i is the three-axis angular velocity value measured by the gyroscope, W is the time window, ||·|| is the two-norm, a i is the three-axis acceleration value measured by the accelerometer, is the mean of the three-axis acceleration in the window, g is the acceleration due to gravity, and are the standard deviations of the acceleration and angular velocity measurement errors, respectively;

[0121] The zero speed thresholds corresponding to the different motion modes are shown in Table 3;

[0122] Table 3 Zero speed detection thresholds for different motion states

[0123]

[0124] S73, identifying various motion modes and adjusting the zero-speed detection threshold corresponding to the motion mode according to the motion mode identification result;

[0125] S8, performing zero speed detection based on the zero speed detection threshold of the motion mode. If the speed is detected to be zero speed, zero speed correction is performed and the process jumps to S9. If the speed is detected to be non-zero speed, zero speed correction is not performed, and the position information is obtained by integrating the speed after zero speed correction and the process jumps to S10.

[0126] The zero speed detection specifically calculates the T value and determines the size of the T value and the zero speed interval threshold γ. If T < γ, it is judged as zero speed; if T ≥ γ, it is judged as non-zero speed;

[0127] S9, perform zero-speed correction on the speed in the zero-speed interval, specifically:

[0128] S91, calculating the a priori estimated state quantity at the current moment;

[0129] The prior estimated state quantity at the current moment is recorded as X(k|k-1) and is calculated by X(k|k-1)=f[X(k-1|k-1)], where X(k-1|k-1) is the optimal estimate at time k-1, also known as the posterior estimate;

[0130] S92, calculating the covariance matrix of the prior estimate;

[0131] The covariance matrix of the prior estimate is denoted as P(k|k-1), and is expressed by P(k|k-1)=F·P(k-1|k-1)·F T +Q calculation, where P(k-1|k-1) is the covariance matrix of X(k-1|k-1), Q is the covariance matrix of the process noise W(k), and F is the Jacobian matrix of the state transfer function f[x] at X(k|k-1);

[0132] S93, calculating the Kalman gain, which is used to update the state by combining the prior estimate and the actual observation value;

[0133] The Kalman gain, denoted as K(k), is obtained by Calculate, where R is the covariance matrix of the observation noise V(k), and H represents the Jacobian matrix of the observation function h[x] at X(k|k-1);

[0134] S94, calculating the optimal estimated state quantity at the current moment;

[0135] The optimal estimated state quantity uses the Kalman gain to correct the prior state estimate to the optimal state estimate, denoted as X(k|k), and is calculated by X(k|k)=X(k|k-1)+K(k)·[Z(k)-h{X(k|k-1)}];

[0136] S95. Calculate the covariance matrix at the current moment to reflect the uncertainty of the latest state estimation;

[0137] The current covariance matrix, denoted as P(k|k), is calculated by P(k|k)=[IK(k)H]·P(k|k-1);

[0138] S10, integrating the speed after zero speed correction to obtain position information;

[0139] The calculated position information is to calculate the position coordinates in the navigation coordinate system, which is recorded as P n ,pass calculate;

[0140] In the hybrid motion mode, the fixed threshold and the adaptive threshold are used to detect the zero speed interval. The detection results of the zero speed interval are as follows: Figure 6 and 7 As shown. Among them, 1 and 0 represent the zero speed moment and non-zero speed moment respectively. Figure 6 It can be seen that in mixed motion, there are 28 and 30 zero-speed intervals in running and walking respectively. There are more missed zero-speed intervals in running state, 13 of which are missed, and the detection rate of zero-speed intervals is 77.6%. Figure 7 It can be seen that the method of adaptively adjusting the zero-speed interval detection threshold based on the motion state can greatly increase the detection rate of the zero-speed interval, and the number of missed zero-speed intervals is 1. The detection rate of the zero-speed interval is 98.3%.

[0141] In hybrid motion mode, the results of zero speed correction based on fixed threshold and adaptive threshold are as follows: Figure 8 and 9 As shown. Figure 8 It can be seen that when there is a missed detection of the zero-speed interval, zero-speed correction cannot be performed in the missed detection interval, which leads to a linear error in the speed. The error gradually accumulates over time, thereby reducing the accuracy of pedestrian inertial navigation. Figure 9It shows that when an adaptive threshold is used to detect the zero-speed interval, the detection rate of the zero-speed interval is higher, the linear error of the speed is reduced, and the speed correction effect is better than that based on the fixed threshold method, which improves the overall performance of the inertial navigation algorithm.

[0142] The motion trajectory drawn based on the fixed threshold method, the motion trajectory drawn based on the adaptive threshold method and the true value of the trajectory are as follows Figure 10 As shown in the figure, the true trajectory is the black solid line, the trajectory of the fixed threshold method is the purple dashed line, and the trajectory of the adaptive threshold method is the blue dashed line. As can be seen from the figure, after correcting the speed within the zero-speed interval detected by the adaptive threshold, the resulting trajectory more accurately reflects the actual motion trajectory than the trajectory obtained by using a fixed threshold to detect the zero-speed interval and then performing zero-speed correction.

[0143] The positioning accuracy based on fixed threshold and adaptive threshold is shown in Table 4. The relative position error of the trajectory obtained by the adaptive threshold method is 1.03m, which is 64.97% lower than the positioning error based on the fixed threshold method, and the relative position error is reduced by 1.17%.

[0144] Table 4 Comparison of positioning accuracy using fixed threshold and adaptive threshold

[0145]

[0146] The above results demonstrate that, compared to other methods, the pedestrian inertial navigation method based on motion recognition can effectively address the issues of missed detection, false detection, and low positioning accuracy that exist in zero-speed interval detection based on a fixed threshold in mixed motion modes. In terms of speed correction and positioning accuracy, its performance is significantly superior to that of the ZUPT algorithm without zero-speed correction and the one based on a fixed threshold, with improved zero-speed interval detection rates and reduced positioning errors.

[0147] At this point, through S1 to S10, a pedestrian inertial navigation method based on motion recognition has been completed in this example, and it has extremely high practicality and obvious advantages.

[0148] The above description is only a preferred embodiment of the present invention, and the present invention should not be limited to the contents disclosed in the embodiment and the accompanying drawings. Any equivalent or modification completed without departing from the spirit disclosed in the present invention shall fall within the scope of protection of the present invention.

Claims

1. A pedestrian inertial navigation method based on motion recognition, characterized in that: The steps include: S1, collect sEMG signals and IMU data through wearable devices; S2, preprocessing the sEMG signal to obtain preprocessed sEMG data; At the same time, in a stationary state, the IMU data is used to calculate the Euler angle and obtain the coordinate rotation matrix, converting the acceleration in the carrier coordinate system to the navigation coordinate system, and obtaining the velocity information after integration; S3, extracting the time domain features, time-frequency features, and time-advance features of the preprocessed sEMG data and combining them to obtain a feature data vector; S4, repeat S1 to S3 multiple times to collect and obtain multiple sets of feature data vectors of different subjects in different motion states, and then divide these feature data vectors into training sets and test sets in proportion; S5. Perform feature screening on the feature data of the training set and update the data set; S6. Construct and train an SVM model based on statistics and motion correction, specifically: traverse the training set and run the SVM model to identify different motion patterns, traverse and obtain the Gaussian kernel bandwidth and penalty coefficient corresponding to the motion pattern with the highest recognition accuracy; statistically analyze the recognition results of the SVM model within a certain time interval, select the motion state recognition result with the mode being the time interval to update the SVM model, and obtain a statistical analysis SVM model; further correct the motion pattern of the previous window by the current estimated motion pattern and update the hyperparameters of the statistical analysis SVM model based on this recognition result, and obtain an SVM model based on statistics and motion correction; S7, adjusting the zero-speed detection threshold of the corresponding motion mode according to the SVM model based on statistics and motion correction of the test set and the motion mode recognition result; S8, performing zero speed detection based on the zero speed detection threshold of the motion mode and the speed information obtained in S2, and if the speed is detected to be zero speed, performing zero speed correction, and then integrating the corrected speed to obtain position information; If the speed is detected to be non-zero, no zero-speed correction is performed, and the speed information obtained by S2 is directly integrated to obtain the position information.

2. The pedestrian inertial navigation method based on motion recognition according to claim 1, characterized in that: The wearable device described in S1 includes electrodes and a sensor group; the sensor group includes an accelerometer, a gyroscope and a magnetometer; the IMU data is obtained by collecting human motion information through the accelerometer, gyroscope and magnetometer; the human motion information includes but is not limited to acceleration information, velocity information and coordinate information.

3. The pedestrian inertial navigation method based on motion recognition according to claim 2, characterized in that: The velocity information is obtained by calculating the Euler angle and obtaining the coordinate rotation matrix in a stationary state, converting the acceleration in the carrier coordinate system to the navigation coordinate system, and then integrating it; the sEMG signal is multi-channel surface electromyography information of the lower limb muscle groups collected based on electrodes in the wearable device; the number of electrodes is greater than 2 and less than 30.

4. The pedestrian inertial navigation method based on motion recognition according to claim 1, characterized in that: The sEMG signal preprocessing step S2 specifically includes the following sub-steps: S21, filtering out high-frequency noise of the sEMG signal by low-pass filtering to obtain a low-pass filtered sEMG signal; S22, performing a first-stage amplification on the low-pass filtered sEMG signal to obtain a first-stage amplified sEMG signal; S23, performing high-pass filtering on the first-stage amplified sEMG signal to obtain a high-pass filtered sEMG signal; S24, performing secondary amplification on the high-pass filtered sEMG signal to obtain a secondary amplified sEMG signal; S25. Convert the secondary amplified sEMG signal into pre-processed sEMG data via an analog-to-digital converter.

5. The pedestrian inertial navigation method based on motion recognition according to claim 4, characterized in that: The cutoff frequency of the low-pass filtering described in S21 is greater than 10Hz and less than 200Hz; the amplification factor of the first-stage amplification described in S22 is greater than or equal to 5 and less than or equal to 100 when implemented; the cutoff frequency of the high-pass filtering described in S23 is greater than or equal to 100Hz and less than or equal to 200Hz, and the high-pass filtering can remove low-frequency noise mainly composed of drift and motion artifacts; the amplification factor of the second-stage amplification described in S24 is greater than or equal to 10 and less than or equal to 200 when implemented.

6. The pedestrian inertial navigation method based on motion recognition according to claim 1, characterized in that: The combination of S3 includes but is not limited to addition, subtraction, series connection and parallel connection; the time domain features, time-frequency features and time-advance features are used to train the SVM model based on statistics and motion correction; the time domain features include but are not limited to MAV, RMS, VARE, IEMG, WL and WA; the time-frequency features include but are not limited to FFT, STFT and wavelet decomposition; the wavelet basis used in the wavelet decomposition includes Haar wavelet basis, dbN wavelet basis, symN or Bior wavelet basis; the number of layers of the wavelet decomposition is greater than or equal to 3 layers and less than or equal to 10 layers in specific implementation; the time-advance feature is extracted based on the advance time window; the value range of the advance time window is greater than or equal to 10ms and less than or equal to 300ms.

7. The pedestrian inertial navigation method based on motion recognition according to claim 6, characterized in that: The specific extraction process of the time-advanced feature is as follows: 1) determining the advance time window; 2) extending the time length of the advance time window from the current time point forward, and adding a fixed time window; 3) extracting the features of the total time length data within the advance time window and the fixed time window; 4) obtaining the features of the total time length data within the advance time window and the fixed time window in sequence with the time step as the interval.

8. The pedestrian inertial navigation method based on motion recognition according to claim 7, characterized in that: The fixed time window has a value range of greater than or equal to 180 ms and less than or equal to 220 ms; the time step has a value range of greater than or equal to 10 ms and less than or equal to 50 ms.

9. The pedestrian inertial navigation method based on motion recognition according to claim 1, characterized in that: The ratio of the training set and the test set in S4 ranges from 6:4 to 9:1; the different motion states include but are not limited to going up stairs, going down stairs, squatting, standing up, standing and walking at a constant speed.

10. The pedestrian inertial navigation method based on motion recognition according to claim 1, characterized in that: S7 is specifically as follows: S71, inputting the test set into the SVM model based on statistics and action correction to perform pattern recognition; S72, drawing a T curve and selecting zero-speed detection thresholds for various motion modes based on the T curve; S73 , identifying various motion modes and adjusting the zero-speed detection threshold corresponding to the motion mode according to the motion mode identification result.

Images