Intelligent motion trail monitoring system and device based on gyroscope dynamic feedback

Abstract

The invention relates to the technical field of motion monitoring, in particular to a motion track intelligent monitoring system and device based on gyroscope dynamic feedback, and the system comprises a motion data monitoring module which obtains the attitude angles of gyroscopes on the left and right sides at each collection moment in each motion period; the motion attitude analysis module is used for calculating the motion difference degree of the single-side gyroscope between any two motion time periods; clustering all motion periods by constructing a weighted undirected graph to obtain left and right dissimilarity degrees of each cluster; dividing all clustering clusters into consistent clusters and different clusters; obtaining a motion fluctuation coefficient of the single-side gyroscope in each different cluster; and the motion posture evaluation module is used for evaluating the stability of the motion track of the motion carrier. According to the method, the movement track of the fancy rope skipping movement can be evaluated, so that whether the movement track of a rope skipping person has stability or not can be accurately evaluated, and the rope skipping person can clearly know the movement effect of each fancy rope skipping action.

Description

Technical Field

[0001] The present application relates to the field of motion monitoring technology, and in particular to a motion trajectory intelligent monitoring system and device based on gyroscope dynamic feedback. Background Art

[0002] As a simple and efficient form of aerobic exercise, rope skipping has a place in national fitness activities due to its low cost, high efficiency and low requirements for venues. Although the traditional rope skipping method can achieve certain exercise purposes, it has obvious limitations in terms of scientificity and personalized guidance. In order to achieve more accurate sports effect evaluation and the design of personalized training programs, the deep integration of smart technology and sports has become an emerging trend.

[0003] When traditional methods are used to evaluate the movement posture of rope skipping, they can only be applied to the scene of standing rope skipping at a uniform speed to detect whether the rhythm of rope skipping is uniform. However, for fancy rope skipping movements, it is impossible to accurately evaluate whether the movement trajectory of the jumper is stable, resulting in limitations in the evaluation and monitoring of the movement trajectory of fancy rope skipping. Summary of the invention

[0004] In order to solve the above technical problems, a motion trajectory intelligent monitoring system and device based on gyroscope dynamic feedback are provided to solve the existing problems.

[0005] The solution to the technical problem of this application is to provide a motion trajectory intelligent monitoring system and device based on gyroscope dynamic feedback, including the following steps:

[0006] In a first aspect, an embodiment of the present application provides a motion trajectory intelligent monitoring system based on gyroscope dynamic feedback, the system comprising:

[0007] The motion data monitoring module is used to record the time required for the motion carrier to move one circle as each motion period, collect the acceleration and angular velocity on both sides of the motion carrier through the gyroscope, perform attitude calculation on it, and obtain the attitude angles of the gyroscopes on the left and right sides at each collection time in each motion period, wherein the attitude angles include pitch angle, roll angle, and yaw angle;

[0008] The motion posture analysis module is used to obtain the left-right dissimilarity of each consistent cluster and the motion fluctuation coefficient of the unilateral gyroscope in each dissimilar cluster, specifically including:

[0009] (1) calculating the motion difference between any two motion periods of the unilateral gyroscope by the differences in the pitch angle, roll angle, and yaw angle of the unilateral gyroscope and the difference in the time length of any two motion periods; clustering all motion periods by constructing a weighted undirected graph based on the motion difference;

[0010] (2) Analyze the changes in the pitch angle, roll angle, and yaw angle of the unilateral gyroscope at each acquisition time in each movement period in each cluster, as well as the discreteness of the difference in the change between the left and right gyroscopes at different acquisition times and the extreme changes in the change, and obtain the left-right dissimilarity of each cluster;

[0011] (3) Based on the left-right dissimilarity, all clusters are divided into consistent clusters and different clusters; the motion fluctuation coefficient of the unilateral gyroscope in each different cluster is obtained by the difference change and fluctuation of the motion difference between different motion periods of the unilateral gyroscope in each different cluster;

[0012] The motion posture evaluation module evaluates the stability of the motion trajectory of the motion carrier based on the left-right dissimilarity of each consistent cluster and the motion fluctuation coefficient of the left and right gyroscopes corresponding to each dissimilar cluster.

[0013] Preferably, the step of calculating the motion difference between any two motion periods of a single-sided gyroscope includes:

[0014] Calculate the difference between the pitch angles of the gyroscope on one side at all acquisition moments in any two motion periods and record it as the relative difference;

[0015] Calculate the difference in time length between any two exercise periods and record it as the time difference;

[0016] The product of the relative difference and the duration difference is used as a first difference coefficient between any two motion periods of the single-sided gyroscope;

[0017] For the roll angle and yaw angle of the single-sided gyroscope at all acquisition moments within any two motion periods, the same method as the first difference coefficient is used to obtain the second difference coefficient and the third difference coefficient between any two motion periods of the single-sided gyroscope;

[0018] The motion difference is an average of the first difference coefficient, the second difference coefficient, and the third difference coefficient.

[0019] Preferably, clustering all exercise periods by constructing a weighted undirected graph includes:

[0020] Select a gyroscope on either side and record it as the target gyroscope;

[0021] Each motion period is taken as a graph node, and there is an edge between any two graph nodes; the inverse of the motion difference between any two motion periods of the target gyroscope is taken as the edge weight between the corresponding two graph nodes to construct a weighted undirected graph;

[0022] Cluster the weighted undirected graph and obtain multiple clusters.

[0023] Preferably, obtaining the left-right dissimilarity of each cluster includes:

[0024] The cumulative sum of the differences in pitch angle, roll angle, and yaw angle of the unilateral gyroscope at any acquisition moment and its adjacent acquisition moment in each movement period in each cluster is taken as the attitude change at any acquisition moment;

[0025] According to the discrete changes of the difference in the attitude change amount between the left and right gyroscopes at different acquisition times in each motion period in each cluster, the motion discreteness of each motion period in each cluster is calculated;

[0026] According to the differences in the maximum attitude change and the minimum attitude change of the left and right gyroscopes in each cluster at each motion period, the extreme difference of each motion period in each cluster is calculated;

[0027] The left-right dissimilarity is the mean of the product of the motion dispersion and the extreme difference in all motion time periods in each cluster.

[0028] Preferably, the calculation of the motion dispersion of each motion period in each cluster includes:

[0029] The difference in attitude change between the left and right gyroscopes at the same acquisition time is recorded as the relative change difference;

[0030] The motion dispersion is the degree of dispersion of the relative change differences at all acquisition moments in each motion period in each cluster.

[0031] Preferably, the calculating of the extreme difference of each exercise period in each cluster includes:

[0032] Calculate the difference in the maximum attitude change between the left and right gyroscopes at all acquisition times in each movement period in each cluster, and record it as the maximum difference;

[0033] Calculate the difference in the minimum attitude change between the left and right gyroscopes at all acquisition times in each movement period in each cluster, and record it as the minimum difference;

[0034] The extreme difference is the sum of the maximum difference and the minimum difference.

[0035] Preferably, the step of dividing all clusters into consistent clusters and distinct clusters includes:

[0036] A threshold segmentation algorithm is used to obtain the segmentation threshold of the left-right dissimilarity of all clusters, and clusters whose left-right dissimilarity is less than or equal to the segmentation threshold are recorded as consistent clusters, otherwise, they are recorded as dissimilar clusters.

[0037] Preferably, obtaining the motion fluctuation coefficient of the single-sided gyroscope in each phase-different cluster includes:

[0038] Arrange all the motion periods in each different cluster in time sequence, and use the motion differences between the first motion period and all other motion periods of the unilateral gyroscope in each different cluster to form a motion difference sequence of the unilateral gyroscope in each different cluster;

[0039] Using all the troughs in the motion difference sequence as segmentation points, the motion difference sequence is divided into a plurality of subsequences;

[0040] Calculate the average of the distances between all two arbitrary subsequences of the unilateral gyroscope in each distinct cluster;

[0041] The motion fluctuation coefficient is the product of the dispersion degree of the mean value of all subsequences of the single-sided gyroscope in each different cluster and the mean value.

[0042] Preferably, the evaluating the stability of the motion trajectory of the motion carrier includes:

[0043] Using an anomaly detection algorithm, perform anomaly detection on the left-right dissimilarity of all consistent clusters and the motion fluctuation coefficients of the left and right gyroscopes corresponding to all dissimilar clusters, and obtain anomaly scores of each consistent cluster and each dissimilar cluster;

[0044] The anomaly scores of all consistent clusters and all different clusters are normalized respectively. If there is a cluster whose normalized anomaly score is greater than or equal to the preset threshold, the motion trajectory of the corresponding cluster is unstable.

[0045] In the second aspect, an embodiment of the present application also provides an intelligent motion trajectory monitoring device based on gyroscope dynamic feedback, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, any one of the above-mentioned intelligent motion trajectory monitoring systems based on gyroscope dynamic feedback is adopted.

[0046] This application has at least the following beneficial effects:

[0047] The present application analyzes the differences in the pitch angle, roll angle, and yaw angle of a unilateral gyroscope in different motion periods and the difference in the duration of different motion periods, and calculates the motion difference of a unilateral gyroscope between any two motion periods. The beneficial effect of the application is that the consistency of the motion trajectory of the unilateral gyroscope in different motion periods is taken into account, and according to the consistency of the motion trajectory of the left and right arms corresponding to the gyroscopes on the left and right sides, all motion periods are clustered, and the motion periods with similar motion trajectories are divided into one category; secondly, the left-right dissimilarity of each cluster is calculated, and the beneficial effect of the application is that the inconsistency of the motion amplitude of the left and right arms corresponding to the gyroscopes on the left and right sides is taken into account, so as to evaluate the degree of the same change of the left and right arms under various motion trajectories; based on the left-right dissimilarity, the fancy movements corresponding to different clusters are distinguished, and the clusters with similar motion trajectories of the left and right arms and the clusters with inconsistent motion trajectories of the left and right arms are classified to obtain each consistent cluster and each Different clusters, finally, according to the discrete changes in the movement difference between the first movement period and the remaining movement periods of the unilateral gyroscope in each different cluster, the movement fluctuation coefficient of the unilateral gyroscope in each different cluster is calculated, which has the beneficial effect of taking into account the difference between the rope skipping movement performed by the unilateral gyroscope in the first movement period in each different cluster and the remaining movement periods, so as to reflect that when the rope jumper performs the rope skipping movement corresponding to the different clusters, the movement trajectory of the arm on the corresponding side of the unilateral gyroscope has repetitive characteristics, thereby evaluating the stability of the running trajectory of different fancy rope skipping movements; abnormal detection is performed on the left and right differences of each consistent cluster and the movement fluctuation coefficient of the left and right gyroscopes corresponding to each different cluster, and the stability of the movement trajectory of the movement carrier is evaluated, which has the beneficial effect of being able to evaluate the movement trajectory of the fancy rope skipping movement, so as to accurately evaluate whether the movement trajectory of the rope jumper is stable, so that the rope jumper can clearly understand the movement effect of each fancy rope skipping action. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The motion trajectory intelligent monitoring system based on gyroscope dynamic feedback of the present application is further described in detail below in conjunction with the accompanying drawings.

[0049] Figure 1 A block diagram of a motion trajectory intelligent monitoring system based on gyroscope dynamic feedback provided in an embodiment of the present application;

[0050] Figure 2 A flowchart of the steps of the motion posture analysis module provided in the embodiment of the present application;

[0051] Figure 3 A flowchart of the steps of a method for obtaining the left-right dissimilarity of each cluster provided in an embodiment of the present application;

[0052] Figure 4A flowchart of the steps of a method for obtaining motion fluctuation coefficients of a single-sided gyroscope in different clusters provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of this application more clear, the following is a further detailed description of the motion trajectory intelligent monitoring system and device based on gyroscope dynamic feedback proposed in this application in conjunction with the accompanying drawings and implementation examples. It should be understood that the specific embodiments described here are only used to explain this application and are not used to limit this application.

[0054] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0055] See also Figure 1 , which shows a block diagram of a motion trajectory intelligent monitoring system based on gyroscope dynamic feedback provided by an embodiment of the present application, the system includes: a motion data monitoring module, a motion posture analysis module, and a motion posture evaluation module:

[0056] The motion data monitoring module is used to collect the acceleration and angular velocity on both sides of the motion carrier through the gyroscope, perform attitude calculation on it, and obtain the attitude angles of the gyroscopes on the left and right sides at each collection moment in each motion period after the motion carrier completes each movement circle, wherein the attitude angles include pitch angle, roll angle, and yaw angle.

[0057] By installing three-axis gyroscopes on the two handles of the skipping rope, a gyroscope is a sensor that can measure angular velocity and acceleration, but its measurement results are based on its own coordinate system. Therefore, the gyroscope needs to be calibrated. When the rope jumper stands still, the gyroscopes on the left and right sides are initially calibrated, and the coordinate system of the gyroscope is aligned with the carrier of the gyroscope, that is, the coordinate system of the skipping rope, and the measurement results in the carrier coordinate system are mapped to the geographic coordinate system to analyze the trajectory and posture of the rope skipping movement.

[0058] When a rope jumper is performing rope jumping, the rope serves as a motion carrier, and the three-axis gyroscopes on the left and right sides collect the acceleration and angular velocity of the motion carrier on which the gyroscopes are located. The data collected by the three-axis gyroscopes are subjected to attitude solution using the quaternion method of the Runge-Kutta method, and the attitude angles of the gyroscopes on the left and right sides at each collection moment are obtained respectively, and the attitude angles include pitch angle, roll angle, and yaw angle.

[0059] It should be noted that the quaternion method of the Runge-Kutta method is a well-known technology and will not be described in detail here.

[0060] Among them, the attitude angle describes the attitude of an object through three consecutive rotations. It is usually expressed by three angles, namely yaw, pitch and roll; yaw: the rotation angle around the vertical axis (usually the z-axis), describing the orientation of the object on the horizontal plane; pitch: the rotation angle around the horizontal axis (usually the y-axis), describing the up and down tilt of the object; roll: the rotation angle around the object's own axis (usually the x-axis), describing the left and right tilt of the object.

[0061] Therefore, the attitude angle of the left gyroscope at the tth acquisition time is in, is the pitch angle of the left gyroscope at the tth acquisition moment; is the roll angle of the left gyroscope at the tth acquisition time, is the yaw angle of the left gyroscope at the tth acquisition time, and the attitude angle of the right gyroscope at the tth acquisition time in, is the pitch angle of the right gyroscope at the tth acquisition moment; is the roll angle of the right gyroscope at the tth acquisition time, is the yaw angle of the right gyroscope at the tth acquisition time.

[0062] A Hall sensor is installed on the rope of the skipping rope to collect the time when the number of circles of the skipping rope changes. Every time the Hall sensor detects that the skipping rope has completed a circle, a time point will be recorded. According to the recorded time points, all the collected moments are divided into multiple exercise periods;

[0063] It should be noted that if a rope jumper jumps N laps, the Hall sensor will record the N changes in the number of laps from the beginning to the end of the rope jumping, and all the collection moments of the entire rope jumping movement collected by the gyroscope will be divided into N+1 movement periods.

[0064] In this embodiment, the acquisition frequency of the three-axis gyroscope and the Hall sensor is 50 Hz, and the acquisition duration is from the start of rope skipping to the end of this rope skipping.

[0065] Thus, the attitude angles of the gyroscopes on the left and right sides at each acquisition moment in each movement period can be obtained respectively.

[0066] The motion posture analysis module is used to obtain the left-right dissimilarity of each consistent cluster and the motion fluctuation coefficient of the single-sided gyroscope in each dissimilar cluster.

[0067] Further, the step flow chart of the motion posture analysis module provided in this embodiment is as follows: Figure 2 shown.

[0068] By analyzing the data collected by the gyroscopes of rope jumpers during rope jumping, it is found that during normal standing rope jumping, the data collected by the left and right gyroscopes have a certain degree of similarity in the change degree at adjacent collection moments, and the motion trajectories collected by the left and right gyroscopes have a certain degree of symmetry. When performing certain fancy rope jumping, the motion trajectories of the left and right gyroscopes are no longer symmetrical, but in the same fancy rope jumping action, due to the repetition of the action, the data collected by the same gyroscope also have a certain degree of similarity.

[0069] Step 1, calculate the motion difference between any two motion periods of the single-sided gyroscope through the differences in the pitch angle, roll angle, yaw angle between any two motion periods, and the difference in the time length of any two motion periods; based on the motion difference, cluster all motion periods by constructing a weighted undirected graph.

[0070] Since different fancy moves require different times to complete a circle, the time periods with similar movements are classified according to the differences in the length of different exercise periods corresponding to different fancy moves and the differences in the data collected in different exercise periods, so as to distinguish different kinds of fancy moves, including:

[0071] Calculate the difference between the pitch angles of the gyroscope on one side at all acquisition moments in any two motion periods and record it as the relative difference;

[0072] In this embodiment, the DTW distance between the pitch angles of a single-sided gyroscope at all acquisition moments within any two motion periods is calculated, wherein the calculation of the DTW distance is a well-known technique and will not be described in detail herein. As other implementation methods, implementers may adopt other methods of the prior art, such as the Euclidean distance, etc., and this embodiment does not impose any special restrictions on this.

[0073] Calculate the difference in time length between any two motion periods of the unilateral gyroscope, and record it as the time difference;

[0074] In this embodiment, the absolute value of the difference in time length between any two motion periods of the single-sided gyroscope is calculated and recorded as the time length difference.

[0075] The product of the relative difference and the time difference is used as the first difference coefficient of any two motion periods of the single-sided gyroscope;

[0076] Similarly, for the roll angle and yaw angle of the single-sided gyroscope at all acquisition moments in any two motion periods, the same method as the first difference coefficient is used to obtain the second difference coefficient and the third difference coefficient of the single-sided gyroscope in any two motion periods.

[0077] It should be noted that the first difference coefficient can reflect the difference in the pitch angle posture changes of the arm on the corresponding side of the gyroscope in different exercise periods; and considering that in fancy rope skipping movements, the posture angle changes in the same direction may also have a high degree of similarity, therefore, the first difference coefficient, the second difference coefficient, and the third difference coefficient are used to measure the changes in the posture angles in all directions to comprehensively reflect the consistency of the movements between the two exercise periods.

[0078] Taking the average of the first difference coefficient, the second difference coefficient and the third difference coefficient as the movement difference of the single-sided gyroscope in any two movement periods;

[0079] It should be noted that the movement difference can reflect the difference between the movement trajectories of the arm of the rope jumper on the corresponding side of the gyroscope in different directions during the exercise period corresponding to two rope skipping circles.

[0080] Furthermore, based on the movement difference, a weighted undirected graph is constructed to perform cluster analysis on all movement periods, specifically:

[0081] Select a gyroscope on either side and record it as the target gyroscope;

[0082] Each motion period is taken as a graph node, and there is an edge between any two graph nodes; the inverse of the motion difference between any two motion periods of the target gyroscope is taken as the edge weight between the corresponding two graph nodes to construct a weighted undirected graph;

[0083] It should be noted that when calculating the inverse of the motion difference of the target gyroscope between any two motion periods, in order to avoid the motion difference being 0, a preset value greater than 0 is added to the denominator. In this embodiment, the preset value greater than 0 is 0.1. As other implementation methods, the implementer can set it according to actual conditions.

[0084] Cluster the weighted undirected graph to obtain multiple clusters;

[0085] In this embodiment, a Markov clustering algorithm is used to cluster the weighted undirected graph to obtain a clustering result for each movement period, wherein the Markov clustering algorithm is a well-known technology and will not be described in detail herein.

[0086] It should be noted that each cluster represents a movement period with similar movement postures, that is, each cluster corresponds to a movement action, so as to distinguish the fancy movements of the arm on the side corresponding to the target gyroscope.

[0087] At this point, multiple clusters are obtained.

[0088] Step 2: Analyze the changes in the pitch angle, roll angle, and yaw angle of the single-side gyroscope at each acquisition time in each motion period in each cluster, as well as the discreteness of the difference in the changes between the left and right gyroscopes at different acquisition times and the extreme changes in the changes, to obtain the left-right dissimilarity of each cluster.

[0089] Furthermore, when a rope jumper is performing fancy rope skipping, the movement trajectories of the rope jumper's left and right arms are relatively corresponding, that is, the movement of the left and right arms at the same collection moment is synchronized in time and amplitude. Secondly, there are certain arm movements in opposite directions in rope skipping, for example, cross jumping. However, the change amplitudes of the left and right arms are consistent, but the change directions in space are inconsistent, which leads to inconsistent posture angles collected by the left and right gyroscopes. Therefore, it is analyzed whether the change amplitudes of the movement trajectories of the left and right arms of the rope jumper are consistent when performing fancy movements corresponding to each cluster, and the left-right dissimilarity is calculated to reflect whether the rope jumper's movements are standard. The step flow chart of the method for obtaining the left-right dissimilarity of each cluster provided in the embodiment of the present application is as follows: Figure 3 As shown, specifically including:

[0090] The cumulative sum of the differences in pitch angle, roll angle, and yaw angle of the unilateral gyroscope between any acquisition moment and the previous acquisition moment in each movement period in each cluster is taken as the attitude change at any acquisition moment;

[0091] In this embodiment, taking the mth motion period in the kth cluster as an example, the calculation formula for the attitude change of the right gyroscope at the tth acquisition time is:

[0092]

[0093] in, is the attitude change of the right gyroscope at the tth acquisition time in the mth motion period in the kth cluster; are the pitch angle, roll angle, and yaw angle of the right gyroscope at the tth acquisition moment in the mth motion period in the kth cluster, respectively. are the pitch angle, roll angle, and yaw angle of the right gyroscope at the t-1th acquisition time in the mth motion period in the kth cluster;

[0094] The calculation formula for the attitude change of the gyroscope on the left at the tth acquisition moment is:

[0095]

[0096] in, is the attitude change of the left gyroscope at the tth acquisition moment in the mth motion period in the kth cluster; are the pitch angle, roll angle, and yaw angle of the gyroscope on the left side at the tth acquisition moment in the mth motion period in the kth cluster, They are the pitch angle, roll angle, and yaw angle of the gyroscope on the left side at the t-1th acquisition moment in the mth motion period in the kth cluster.

[0097] The difference in the attitude change between the left and right gyroscopes at any acquisition moment is recorded as a relative change difference;

[0098] In this embodiment, the absolute value of the difference between the attitude change amounts of the left and right gyroscopes at any acquisition moment is recorded as the relative change difference.

[0099] Calculating the discrete degree of the relative change difference at all acquisition moments in each motion period in each cluster as the motion discrete degree of each motion period in each cluster;

[0100] In this embodiment, the degree of dispersion is measured by calculating the variance of the relative change difference of all acquisition moments in each motion period in each cluster. As other implementation methods, implementers can adopt other methods of the prior art, such as the coefficient of variation, etc. This embodiment does not impose any special restrictions on this.

[0101] It should be noted that the smaller the relative change difference is, the closer the movement amplitudes of the left and right arms are at the same acquisition time, and the smaller the movement discreteness is, which means that within the same movement period, the fluctuation of the difference in the change amplitude of the movement trajectories of the left and right arms is smaller, and the changes in the movement trajectories of the left and right arms are more consistent.

[0102] Calculate the difference in the maximum attitude change between the left and right gyroscopes at all acquisition times in each movement period in each cluster, and record it as the maximum difference;

[0103] Calculate the difference in the minimum attitude change between the left and right gyroscopes at all acquisition times in each movement period in each cluster, and record it as the minimum difference;

[0104] In this embodiment, the absolute value of the difference in the maximum posture change amount between the left and right gyroscopes at all acquisition moments in each motion period in each cluster is calculated, which is recorded as the maximum difference; the absolute value of the difference in the minimum posture change amount between the left and right gyroscopes at all acquisition moments in each motion period in each cluster is calculated, which is recorded as the minimum difference.

[0105] The sum of the maximum difference and the minimum difference is taken as the extreme difference of each exercise period in each cluster;

[0106] The mean of the product of the motion dispersion and the extreme difference in all motion periods in each cluster is used as the left-right dissimilarity of each cluster;

[0107] It should be noted that the extreme difference reflects the difference between the maximum and minimum change amplitudes of the left and right arms in the same exercise period. The smaller the extreme difference, the smaller the left-right dissimilarity, indicating that when the rope jumper completes the exercise action corresponding to the cluster, the change amplitude of the movement trajectory of the left and right arms in each circle of rope skipping is relatively consistent, reflecting that the movement posture of the rope jumper when completing the exercise action corresponding to the cluster is more stable, and the possibility of conforming to the standard rope skipping trajectory is greater.

[0108] At this point, the left-right dissimilarity of each cluster is obtained.

[0109] Step 3, based on the left-right dissimilarity, all clustering clusters are divided into consistent clusters and different clusters; the motion fluctuation coefficient of the unilateral gyroscope in each different cluster is obtained through the difference changes and fluctuations of the motion difference between different motion periods in each different cluster.

[0110] In fancy rope skipping, not all movements have the same changes in the left and right arms, so it is necessary to distinguish the movements with inconsistent left and right arm movements. That is, based on the left and right dissimilarity of all clusters, the clusters corresponding to the inconsistent left and right arm movements are distinguished, specifically:

[0111] Using a threshold segmentation algorithm, obtain the segmentation threshold of the left-right dissimilarity of all clusters, record the clusters whose left-right dissimilarity is less than or equal to the segmentation threshold as consistent clusters, otherwise, record them as dissimilar clusters;

[0112] In this embodiment, the Otsu threshold segmentation algorithm is used for threshold segmentation, wherein the Otsu threshold segmentation algorithm is a well-known technology and will not be described in detail here.

[0113] Furthermore, in fancy rope skipping, although the trajectory changes of the two arms in the same set of fancy movements may be inconsistent, the movement trajectory of a single arm will show a certain degree of repeatability. Therefore, by analyzing whether the movement trajectory of a single arm in different numbers of circles in the same set of fancy movements is repeatable and calculating the movement fluctuation coefficient, the stability of the rope skipper when performing fancy movements can be evaluated. The step flow chart of the method for obtaining the movement fluctuation coefficient of a single-sided gyroscope in each phase different cluster provided in the embodiment of the present application is as follows: Figure 4 As shown, specifically including:

[0114] Arrange all the motion periods in each different cluster in time sequence, and use the motion differences between the first motion period and all other motion periods of the unilateral gyroscope in each different cluster to form a motion difference sequence of the unilateral gyroscope in each different cluster;

[0115] It should be noted that, for ease of understanding, it is assumed that all motion periods in the qth different cluster are I3, I5, I7, and I8, and the motion difference between the right gyroscope in the I3th motion period and the I5th motion period is α 3.5 The difference between the right gyroscope's motion in the I3th and I7th motion periods is α 3.7 The difference between the right gyroscope's motion in the 13th motion period and the 18th motion period is α 3.8 , then the motion difference sequence of the right gyroscope in the qth different cluster is [α 3.5 ,α 3.7 ,α 3.8 ].

[0116] It should be noted that the motion difference sequence reflects the degree of difference in the change of the motion trajectory of the arm on the corresponding side of the unilateral gyroscope between the first jump circle and all subsequent jump circles in the fancy movements corresponding to each phase-different cluster.

[0117] Secondly, considering that the movement trajectory of the unilateral arm is repetitive, it may be repeated after several laps, that is, the movement trajectory of the unilateral arm is repeated, but it is separated by a certain movement period. If the movement difference between the two movement periods is small, the movement trajectory of the right arm in the two movement periods is relatively consistent. Therefore, the movement difference sequence can be divided into multiple subsequences by performing trough analysis on the movement difference sequence to determine whether the movement change of the unilateral arm is staged and regular.

[0118] Using all the troughs in the motion difference sequence as segmentation points, the motion difference sequence is divided into a plurality of subsequences;

[0119] In this embodiment, a difference method is used to obtain all the troughs in the motion difference sequence.

[0120] Calculate the average of the distances between all two arbitrary subsequences of the unilateral gyroscope in each distinct cluster;

[0121] In this embodiment, the average value of the DTW distance between all arbitrary two subsequences of the single-sided gyroscope in each different cluster is calculated, wherein the calculation of the DTW distance is a well-known technology and will not be repeated here. As other implementation methods, the implementer may adopt other methods of the prior art, such as the Euclidean distance, etc., and this embodiment does not impose any special restrictions on this.

[0122] Calculate the product of the discrete degree of the mean value of all subsequences of the unilateral gyroscope in each phase-different cluster and the mean value as the motion fluctuation coefficient of the unilateral gyroscope in each phase-different cluster;

[0123] It should be noted that the average value reflects the difference in the motion trajectory of the unilateral arm at different stages under the fancy movements corresponding to different clusters. The smaller the average value is, the more repeatable the motion trajectory of the unilateral arm is. The discrete degree of the mean of all subsequences of the unilateral gyroscope in each different cluster reflects whether the motion trajectory of the unilateral arm at different stages is relatively stable. The smaller the obtained motion fluctuation coefficient is, the more stable the movements of the rope jumper under the fancy movements corresponding to different clusters are. The motion fluctuation coefficient takes into account the possible intervals in the repetitive changes of the unilateral arm. By analyzing the motion difference sequence in stages, it is possible to accurately and comprehensively reflect whether the motion trajectory of the unilateral arm is stable regardless of whether there are intervals between the repetitive changes of the unilateral arm, thereby more accurately evaluating the stability of the rope jumper when performing fancy movements.

[0124] So far, the motion fluctuation coefficient of the single-sided gyroscope in each phase-different cluster is obtained.

[0125] The motion posture evaluation module evaluates the stability of the motion trajectory of the motion carrier based on the left-right dissimilarity of each consistent cluster and the motion fluctuation coefficient of the left and right gyroscopes corresponding to each dissimilar cluster.

[0126] Further, based on the left-right dissimilarity of all consistent clusters and the motion fluctuation coefficients of the left and right gyroscopes corresponding to all dissimilar clusters, the stability of the motion trajectory of the moving carrier is evaluated, specifically:

[0127] Using an anomaly detection algorithm, perform anomaly detection on the left-right dissimilarity of all consistent clusters to obtain an anomaly score for each consistent cluster;

[0128] Using an anomaly detection algorithm, anomaly detection is performed on the motion fluctuation coefficients of the left and right gyroscopes corresponding to all different clusters to obtain anomaly scores for each different cluster;

[0129] In this embodiment, a LOF (Local Outliers Factor) anomaly detection algorithm is used to perform anomaly detection, wherein the LOF anomaly detection algorithm is a well-known technology and will not be described in detail herein.

[0130] The anomaly scores of all consistent clusters and all different clusters are normalized respectively. If there is a cluster whose normalized anomaly score is greater than or equal to the preset threshold, the motion trajectory of the corresponding cluster is unstable.

[0131] In this embodiment, the preset threshold value is 0.5. As for other implementation modes, the implementer can set it according to the actual situation.

[0132] It should be noted that if there is a cluster whose normalized abnormal score is greater than or equal to the preset threshold, it means that when the rope jumper performs the fancy movements corresponding to the cluster, the movement trajectory of the arm fluctuates greatly, and the rope jumper does not have a good exercise effect on the rope jumping movement. In this case, the rope jumper can repeat the rope jumping movement.

[0133] Based on the same inventive concept as the above-mentioned system, an embodiment of the present application also provides an intelligent motion trajectory monitoring device based on gyroscope dynamic feedback, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, any one of the above-mentioned intelligent motion trajectory monitoring systems based on gyroscope dynamic feedback is adopted.

[0134] It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0135] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0136] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the present application. It should be pointed out that, for those of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present application without departing from the content of the technical solution of the present application, shall fall within the protection scope of the technical solution of the present application.

Claims

1. The motion trajectory intelligent monitoring system based on gyroscope dynamic feedback is characterized by: The system includes: The motion data monitoring module is used to record the time required for the motion carrier to move one circle as each motion period, collect the acceleration and angular velocity on both sides of the motion carrier through the gyroscope, perform attitude calculation on it, and obtain the attitude angles of the gyroscopes on the left and right sides at each collection time in each motion period, wherein the attitude angles include pitch angle, roll angle, and yaw angle; The motion posture analysis module is used to obtain the left-right dissimilarity of each consistent cluster and the motion fluctuation coefficient of the unilateral gyroscope in each dissimilar cluster, specifically including: (1) calculating the motion difference between any two motion periods of the unilateral gyroscope by the differences in the pitch angle, roll angle, and yaw angle of the unilateral gyroscope and the difference in the time length of any two motion periods; clustering all motion periods by constructing a weighted undirected graph based on the motion difference; (2) Analyze the changes in the pitch angle, roll angle, and yaw angle of the unilateral gyroscope at each acquisition time in each movement period in each cluster, as well as the discreteness of the difference in the change between the left and right gyroscopes at different acquisition times and the extreme changes in the change, and obtain the left-right dissimilarity of each cluster; (3) Based on the left-right dissimilarity, all clusters are divided into consistent clusters and different clusters; the motion fluctuation coefficient of the unilateral gyroscope in each different cluster is obtained by the difference change and fluctuation of the motion difference between different motion periods of the unilateral gyroscope in each different cluster; The motion posture evaluation module evaluates the stability of the motion trajectory of the motion carrier based on the left-right dissimilarity of each consistent cluster and the motion fluctuation coefficient of the left and right gyroscopes corresponding to each dissimilar cluster.

2. The motion trajectory intelligent monitoring system based on gyroscope dynamic feedback as claimed in claim 1, characterized in that: The step of calculating the motion difference between any two motion periods of a single-sided gyroscope comprises: Calculate the difference between the pitch angles of the gyroscope on one side at all acquisition moments in any two motion periods and record it as the relative difference; Calculate the difference in time length between any two exercise periods and record it as the time difference; The product of the relative difference and the duration difference is used as a first difference coefficient between any two motion periods of the single-sided gyroscope; For the roll angle and yaw angle of the single-sided gyroscope at all acquisition moments within any two motion periods, the same method as the first difference coefficient is used to obtain the second difference coefficient and the third difference coefficient between any two motion periods of the single-sided gyroscope; The motion difference is an average of the first difference coefficient, the second difference coefficient, and the third difference coefficient.

3. The motion trajectory intelligent monitoring system based on gyroscope dynamic feedback as claimed in claim 1, characterized in that: The method clusters all the motion periods by constructing a weighted undirected graph, including: Select a gyroscope on either side and record it as the target gyroscope; Each motion period is taken as a graph node, and there is an edge between any two graph nodes; the inverse of the motion difference between any two motion periods of the target gyroscope is taken as the edge weight between the corresponding two graph nodes to construct a weighted undirected graph; Cluster the weighted undirected graph and obtain multiple clusters.

4. The motion trajectory intelligent monitoring system based on gyroscope dynamic feedback as claimed in claim 1, characterized in that: The left-right dissimilarity of each cluster is obtained, including: The cumulative sum of the differences in pitch angle, roll angle, and yaw angle of the unilateral gyroscope at any acquisition moment and its adjacent acquisition moment in each movement period in each cluster is taken as the attitude change at any acquisition moment; According to the discrete changes of the difference in the attitude change amount between the left and right gyroscopes at different acquisition times in each motion period in each cluster, the motion discreteness of each motion period in each cluster is calculated; According to the differences in the maximum attitude change and the minimum attitude change of the left and right gyroscopes in each cluster at each motion period, the extreme difference of each motion period in each cluster is calculated; The left-right dissimilarity is the mean of the product of the motion dispersion and the extreme difference in all motion time periods in each cluster.

5. The motion trajectory intelligent monitoring system based on gyroscope dynamic feedback as claimed in claim 4, characterized in that: The step of calculating the motion discreteness of each motion period in each cluster includes: The difference in attitude change between the left and right gyroscopes at the same acquisition time is recorded as the relative change difference; The motion dispersion is the degree of dispersion of the relative change differences at all acquisition moments in each motion period in each cluster.

6. The motion trajectory intelligent monitoring system based on gyroscope dynamic feedback as claimed in claim 4, characterized in that: The calculation of the extreme difference of each exercise period in each cluster includes: Calculate the difference in the maximum attitude change between the left and right gyroscopes at all acquisition times in each movement period in each cluster, and record it as the maximum difference; Calculate the difference in the minimum attitude change between the left and right gyroscopes at all acquisition times in each movement period in each cluster, and record it as the minimum difference; The extreme difference is the sum of the maximum difference and the minimum difference.

7. The motion trajectory intelligent monitoring system based on gyroscope dynamic feedback as claimed in claim 1, characterized in that: The method of dividing all clusters into consistent clusters and different clusters includes: A threshold segmentation algorithm is used to obtain the segmentation threshold of the left-right dissimilarity of all clusters, and clusters whose left-right dissimilarity is less than or equal to the segmentation threshold are recorded as consistent clusters, otherwise, they are recorded as dissimilar clusters.

8. The motion trajectory intelligent monitoring system based on gyroscope dynamic feedback as claimed in claim 1, characterized in that: The motion fluctuation coefficients of the unilateral gyroscope in each phase-different cluster are obtained, including: Arrange all the motion periods in each different cluster in time sequence, and use the motion differences between the first motion period and all other motion periods of the unilateral gyroscope in each different cluster to form a motion difference sequence of the unilateral gyroscope in each different cluster; Using all the troughs in the motion difference sequence as segmentation points, the motion difference sequence is divided into a plurality of subsequences; Calculate the average of the distances between all two arbitrary subsequences of the unilateral gyroscope in each distinct cluster; The motion fluctuation coefficient is the product of the dispersion degree of the mean value of all subsequences of the single-sided gyroscope in each different cluster and the mean value.

9. The motion trajectory intelligent monitoring system based on gyroscope dynamic feedback as claimed in claim 1, characterized in that: The evaluating the stability of the motion trajectory of the motion carrier includes: Using an anomaly detection algorithm, perform anomaly detection on the left-right dissimilarity of all consistent clusters and the motion fluctuation coefficients of the left and right gyroscopes corresponding to all dissimilar clusters, and obtain anomaly scores of each consistent cluster and each dissimilar cluster; The anomaly scores of all consistent clusters and all different clusters are normalized respectively. If there is a cluster whose normalized anomaly score is greater than or equal to the preset threshold, the motion trajectory of the corresponding cluster is unstable.

10. A motion trajectory intelligent monitoring device based on gyroscope dynamic feedback, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the motion trajectory intelligent monitoring system based on gyroscope dynamic feedback as described in any one of claims 1-9 is adopted.

Images