Postoperative rehabilitation quantitative evaluation method and system for elbow joint based on three-dimensional motion capture

Abstract

This invention relates to the field of intelligent data processing technology, and discloses a method, system, computer equipment, and storage medium for quantitative assessment of postoperative rehabilitation of the elbow joint based on three-dimensional motion capture. The method includes: acquiring the spatiotemporal coordinates of shoulder, elbow, and wrist landmarks on the affected upper limb during continuous cyclic flexion and extension movements; constructing upper arm and forearm vectors based on the landmark coordinates to generate elbow joint angle time series and elbow joint angular velocity time series; reconstructing the angle time series into phase space to generate an angle phase space trajectory, and calculating the angle fluctuation complexity index based on its geometric morphological characteristics; performing symbolic dynamic analysis on the angular velocity time series to generate a symbolic entropy value for angular velocity; and inputting the two indices into a rehabilitation quantitative assessment model for multi-dimensional fusion calculation to generate a comprehensive rehabilitation quantitative score. This application achieves a quantitative assessment of the stability and smoothness of elbow joint movement, providing objective data support for clinical rehabilitation.

Description

Technical Field

[0001] This invention relates to the field of intelligent data processing technology, specifically to a method, system, computer equipment, and storage medium for quantitative assessment of postoperative rehabilitation of the elbow joint based on three-dimensional motion capture. Background Technology

[0002] Postoperative rehabilitation assessment of the elbow joint is crucial for determining the patient's functional recovery and guiding adjustments to the rehabilitation training program. Currently, commonly used clinical assessment methods include joint range of motion measurements, manual muscle strength tests, and various functional scoring scales. However, these methods rely heavily on manual measurement and subjective judgment, only obtaining static indicators such as joint range of motion and muscle strength levels. They cannot quantify the dynamic control ability during movement and therefore cannot objectively reflect the true level of neuromuscular functional recovery. While existing motion capture-based assessment technologies can acquire kinematic data, they typically only compare angle curves, lacking in-depth quantitative analysis of characteristics reflecting the quality of motor control, such as movement smoothness and velocity continuity. This leads to discrepancies between assessment results and the patient's actual functional status. Summary of the Invention

[0003] Therefore, it is necessary to provide a method, system, computer equipment, and storage medium for postoperative elbow joint rehabilitation quantitative assessment based on three-dimensional motion capture, which can capture and acquire elbow joint motion data and extract multi-dimensional motion control features to generate a comprehensive rehabilitation quantitative score.

[0004] In a first aspect, the present invention discloses a quantitative assessment method for postoperative rehabilitation of the elbow joint based on three-dimensional motion capture, the method comprising: The spatiotemporal coordinates of the shoulder, elbow, and wrist landmarks of the affected upper limb were collected using a three-dimensional motion capture system when the subject performed continuous cyclic flexion and extension movements. Based on the spatiotemporal coordinates of the shoulder marker, the elbow marker, and the wrist marker, an upper arm vector and a forearm vector are constructed. Based on the real-time spatial angle between the upper arm vector and the forearm vector, an elbow joint angle time series and an elbow joint angular velocity time series are generated. The elbow joint angle time series is reconstructed in phase space to generate an angle phase space trajectory, and the angle fluctuation complexity index is calculated based on the geometric morphology characteristics of the angle phase space trajectory; and the elbow joint angular velocity time series is subjected to symbolic dynamic analysis to generate a symbolic entropy value of angular velocity based on the time distribution of angular velocity values. The angle fluctuation complexity index and the angular velocity symbolic entropy value are input into a pre-constructed rehabilitation quantitative assessment model. The rehabilitation quantitative assessment model performs multi-dimensional fusion calculation on the angle fluctuation complexity index and the angular velocity symbolic entropy value to generate a comprehensive quantitative score for the subject's elbow joint postoperative rehabilitation.

[0005] It is feasible that the continuous cyclic flexion and extension movement includes a flexion phase in which the elbow joint moves from an extended state to a flexed state and an extension phase in which the elbow joint moves from a flexed state to an extended state, and the continuous cyclic flexion and extension movement is performed at least ten times.

[0006] In one embodiment, calculating the angle fluctuation complexity index based on the geometric morphological characteristics of the angle phase space trajectory includes: The elbow joint angle time series is embedded with a time delay to construct a two-dimensional phase space trajectory with the current angle value as the first dimension and the angle value after a preset time step delay as the second dimension. Calculate the area covered by the trajectory points of the two-dimensional phase space trajectory, and use it as the trajectory extension feature; The dispersion of the distance distribution between each trajectory point and the trajectory center point on the two-dimensional phase space trajectory is calculated as a trajectory clustering feature. The angle fluctuation complexity index is generated based on a weighted combination of the trajectory expansion features and the trajectory aggregation features.

[0007] In one embodiment, the angular fluctuation complexity index includes phase space trajectory area and phase space trajectory dispersion, wherein the phase space trajectory area is used to characterize the range of elbow joint angle changes, and the phase space trajectory dispersion is used to characterize the degree of trajectory clustering of elbow joint angle changes.

[0008] In one embodiment, the symbolic dynamic analysis of the elbow joint angular velocity time series, generating a symbolic entropy value of angular velocity based on the time distribution of the angular velocity values, includes: According to a preset angular velocity threshold, the angular velocity values ​​at each moment in the elbow joint angular velocity time series are converted into an angular velocity symbol sequence composed of a first symbol and a second symbol, wherein angular velocity values ​​greater than or equal to the preset threshold are converted into the first symbol, and angular velocity values ​​less than the preset threshold are converted into the second symbol. The angular velocity symbol sequence is segmented using a sliding window of fixed length to generate multiple symbol subsequences; The frequency of occurrence of each symbol subsequence in the plurality of symbol subsequences is statistically analyzed, and the angular velocity symbolization entropy value is calculated based on the uniformity of the distribution of the frequency of occurrence.

[0009] In one embodiment, the process of constructing the rehabilitation quantitative assessment model includes: The spatiotemporal coordinates of the shoulder markers, elbow markers, and wrist markers of the healthy control group were acquired by the three-dimensional motion capture system when performing the continuous cyclic flexion and extension movements. Based on the spatiotemporal coordinates of the shoulder markers, elbow markers, and wrist markers of the control group, a time series of elbow joint angles and a time series of elbow joint angular velocities of the control group are generated. Based on the time series of elbow joint angles and the time series of elbow joint angular velocities of the control group, an angle fluctuation complexity index and a symbolic entropy value of angular velocity of the control group are calculated. A multidimensional motion control feature set of the control group is generated, consisting of the angle fluctuation complexity index and the symbolic entropy value of angular velocity of the control group. The multidimensional control group's motor control feature set is fitted with a probability distribution to generate a standard motor control parameter set corresponding to the continuous cyclic flexion-extension movement. The standard motor control parameter set includes the probability density function of each feature dimension in the multidimensional control group's motor control feature set and the confidence interval boundary determined based on the probability density function.

[0010] In one embodiment, generating the subject's post-operative elbow joint rehabilitation quantitative comprehensive score includes: Based on the quantile positions of the angle fluctuation complexity index and the symbolic entropy value of the angular velocity in the probability density function of the standard motion control parameter set, determine the index quantile matching degree corresponding to the angle fluctuation complexity index and the entropy value quantile matching degree corresponding to the symbolic entropy value of the angular velocity; A basic score is generated based on the weighted sum of the quantile matching degree of the indicator and the quantile matching degree of the entropy value; The cumulative number of times the angle fluctuation complexity index and the symbolic entropy value of the angular velocity cross the boundary of the confidence interval per unit time is counted, and a stability decay coefficient is generated based on the relationship between the cumulative number and the preset number threshold. The comprehensive rehabilitation score is generated by combining the baseline score and the stability decay coefficient.

[0011] In one embodiment, generating the comprehensive rehabilitation score based on the combination of the baseline score and the stability decay coefficient includes: When the stability decay coefficient is less than or equal to the preset decay threshold, the basic score is used as the comprehensive rehabilitation quantitative score. When the stability decay coefficient is greater than the preset decay threshold, the basic score is decayed according to the ratio of the difference between the stability decay coefficient and the preset decay threshold, and the score after decay is used as the comprehensive rehabilitation quantitative score.

[0012] Secondly, this application discloses a system corresponding to the aforementioned quantitative assessment method for postoperative rehabilitation of the elbow joint based on three-dimensional motion capture, the system comprising: The data acquisition module is configured to acquire the spatiotemporal coordinates of the shoulder, elbow, and wrist landmarks of the affected upper limb of the subject when performing continuous cyclic flexion and extension movements, as collected by the three-dimensional motion capture system. The parameter calculation module is configured to construct an upper arm vector and a forearm vector based on the spatiotemporal coordinates of the shoulder marker, the elbow marker, and the wrist marker, and to generate an elbow joint angle time series and an elbow joint angular velocity time series based on the real-time spatial angle between the upper arm vector and the forearm vector. The feature extraction module is configured to reconstruct the phase space of the elbow joint angle time series, generate the angle phase space trajectory, and calculate the angle fluctuation complexity index based on the geometric morphology features of the angle phase space trajectory; and to perform symbolic dynamic analysis on the elbow joint angular velocity time series, and generate symbolic entropy values ​​of angular velocity based on the time distribution of angular velocity values. The rehabilitation assessment module is configured to input the angle fluctuation complexity index and the angular velocity symbolic entropy value into a pre-built rehabilitation quantitative assessment model, and to perform multi-dimensional fusion calculation on the angle fluctuation complexity index and the angular velocity symbolic entropy value through the rehabilitation quantitative assessment model to generate a comprehensive quantitative score for the subject's elbow joint postoperative rehabilitation.

[0013] Thirdly, this application discloses a computer device, including a memory and a processor, wherein the memory is communicatively connected to the processor, and the memory stores a computer program that can be executed by the processor. When the computer program is executed by the processor, the above-described method for quantitative assessment of postoperative elbow joint rehabilitation based on three-dimensional motion capture is implemented.

[0014] Fourthly, this application discloses a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described method for quantitative assessment of postoperative elbow joint rehabilitation based on three-dimensional motion capture.

[0015] Compared with the prior art, the method, system, computer equipment and storage medium for quantitative assessment of postoperative rehabilitation of elbow joint based on three-dimensional motion capture of the present invention have at least the following beneficial effects: A three-dimensional motion capture system was used to collect the spatiotemporal coordinates of shoulder, elbow, and wrist landmarks on the affected upper limb during continuous cyclic flexion and extension movements, providing a precise foundation of motion data for subsequent analysis. Upper arm and forearm vectors were constructed based on the collected landmark spatiotemporal coordinates, and elbow joint angle and angular velocity time series were generated based on real-time spatial angles, achieving accurate calculation of kinematic parameters from raw coordinate data. By reconstructing the elbow joint angle time series into phase space to generate an angle phase space trajectory, and calculating the angle fluctuation complexity index based on its geometric morphology, the smoothness characteristics of elbow joint movement can be quantified, effectively identifying the presence of abnormal movement patterns such as shaking or stuttering. Symbolic dynamic analysis of the elbow joint angular velocity time series generated symbolic angular velocity entropy values, quantifying the smoothness characteristics of elbow joint movement and accurately capturing the continuity and regularity of velocity changes. The angular fluctuation complexity index and the symbolic entropy value of angular velocity are input into a pre-constructed rehabilitation quantitative assessment model for multi-dimensional fusion calculation, and finally generate a comprehensive quantitative score for postoperative rehabilitation of elbow joint. This achieves a comprehensive quantitative assessment of the patient's dynamic control ability from two dimensions: motion stability and motion fluency, providing objective and accurate data processing results for clinical practice. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram illustrating an application scenario of a quantitative assessment method for postoperative rehabilitation of the elbow joint based on three-dimensional motion capture in one embodiment. Figure 2 This is a flowchart of a quantitative assessment method for postoperative rehabilitation of the elbow joint based on three-dimensional motion capture in one embodiment. Figure 3 This is a structural block diagram of a quantitative assessment system for postoperative rehabilitation of elbow joint based on three-dimensional motion capture in one embodiment. Figure 4 This is a schematic diagram of the structure of a computer device in one embodiment. Detailed Implementation

[0018] To facilitate understanding of the technical solutions provided in the embodiments of this application, the background technology involved in the embodiments of this application will be described below.

[0019] Postoperative rehabilitation assessment of the elbow joint is crucial for determining the patient's functional recovery and guiding adjustments to the rehabilitation training program. Currently, commonly used clinical assessment methods include joint range of motion measurements, manual muscle strength tests, and various functional scoring scales. These methods primarily rely on manual measurement and subjective judgment, obtaining static indicators such as joint range of motion and muscle strength levels, providing some reference for clinical rehabilitation decisions. However, elbow joint function recovery is not only reflected in improved range of motion and increased muscle strength, but also in the precise control of the joint during movement, including dynamic characteristics such as the smoothness of the movement trajectory and the continuity of speed changes. Existing clinical assessment methods struggle to quantify these dynamic control capabilities and cannot fully reflect the true level of neuromuscular function recovery.

[0020] With the development of motion capture technology, assessment methods based on three-dimensional motion capture are gradually being applied in the field of rehabilitation. Existing technologies use three-dimensional motion capture systems to acquire the spatial coordinates of key points on the subject's upper limbs, then calculate the elbow joint angle change curve, and assess the rehabilitation effect by comparing it with a standard curve. However, these methods typically only focus on the morphological comparison of the angle curve, failing to deeply mine the dynamic control information inherent in the movement from the perspective of nonlinear dynamics. Angle curve comparison can only reflect the external morphology of the movement, making it difficult to quantify the internal control quality of the movement. For example, whether there are abnormal patterns such as shaking or stuttering during the movement, and whether the speed changes are continuous and regular—these key characteristics reflecting the quality of motor control cannot be effectively extracted and quantified in current assessment methods.

[0021] Therefore, how to extract deep features that can characterize the quality of elbow joint motion control from three-dimensional motion capture data and achieve an objective quantitative assessment of the postoperative rehabilitation effect of elbow joint is a technical problem that urgently needs to be solved by those skilled in the art.

[0022] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present application.

[0023] Before describing the technical solutions provided in the embodiments of this application, the data collection and use involved in the embodiments of this application will first be explained. The spatiotemporal coordinates of shoulder landmarks, elbow landmarks, and wrist landmarks collected in the embodiments of this application for both subjects and healthy control groups were all collected by qualified rehabilitation physicians or technicians according to standard operating procedures, with the explicit informed consent of the subjects or their legal guardians. The collection, storage, processing, and use of the data strictly comply with relevant laws and regulations and privacy protection policies to ensure the security of the subjects' personal information.

[0024] The quantitative assessment method for postoperative rehabilitation of the elbow joint based on three-dimensional motion capture, as described in this application, can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. Specifically, a three-dimensional motion capture system is connected to terminal 102 to collect the spatiotemporal coordinates of shoulder, elbow, and wrist landmarks of the subject's affected upper limb during continuous cyclic flexion and extension movements. After acquiring the aforementioned landmark spatiotemporal coordinates, terminal 102 can construct upper arm and forearm vectors based on the shoulder, elbow, and wrist landmark coordinates, and generate elbow joint angle time series and elbow joint angular velocity time series based on the real-time spatial angle between the upper arm and forearm vectors. Terminal 102 can send the generated elbow joint angle time series and elbow joint angular velocity time series to server 104, where server 104 performs subsequent processing steps: reconstructing the phase space of the elbow joint angle time series to generate an angle phase space trajectory, and calculating the angle fluctuation complexity index based on the geometric characteristics of the angle phase space trajectory; performing symbolic dynamic analysis on the elbow joint angular velocity time series, generating a symbolic entropy value of angular velocity based on the time distribution of angular velocity values; inputting the angle fluctuation complexity index and the symbolic entropy value of angular velocity into a pre-constructed rehabilitation quantitative assessment model, and performing multi-dimensional fusion calculation of the angle fluctuation complexity index and the symbolic entropy value of angular velocity through the rehabilitation quantitative assessment model to generate a comprehensive quantitative score for the subject's postoperative elbow joint rehabilitation. Server 104 returns the generated comprehensive quantitative score to terminal 102 for display or storage. In another embodiment, terminal 102 can also complete all the above processing steps independently without communicating with server 104. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices, and server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0025] In summary, the core technical challenge in clinical practice of elbow postoperative rehabilitation assessment lies in extracting deep-seated features from motion data that truly reflect the quality of neuromuscular control. Existing assessment methods primarily rely on static angle measurements or simple curve comparisons, failing to quantify the smoothness and fluidity of the movement process, thus making it difficult for assessment results to fully reflect the patient's true functional recovery status.

[0026] To address the aforementioned technical problems, firstly, this embodiment provides a quantitative assessment method for postoperative rehabilitation of the elbow joint based on three-dimensional motion capture. Taking the terminal 102 mentioned above as an example, for instance... Figure 2 As shown, the method includes: a data acquisition step, a parameter calculation step, a feature extraction step, and a rehabilitation assessment step.

[0027] Specifically, the data acquisition steps include: collecting the spatiotemporal coordinates of the shoulder, elbow, and wrist landmarks of the subject's affected upper limb when performing continuous cyclic flexion and extension movements using a three-dimensional motion capture system.

[0028] In this step, the three-dimensional motion capture system used can be an optical motion capture system, such as a commercial motion capture system manufactured by companies like MotionAnalysis Corporation, Vicon, or OptiTrack. This system uses multiple high-speed cameras to simultaneously capture the spatial positions of reflective markers attached to the subject's skin surface. In practical applications, inertial or electromagnetic motion capture systems can also be used; this application does not limit the specific type. Shoulder markers are typically attached to the acromion, elbow markers to the lateral epicondyle of the humerus, and wrist markers to the midpoint of the line connecting the radial and ulnar styloid processes. During the data collection process, the subject performs continuous cyclic flexion and extension movements as instructed by the rehabilitation physician. Starting from full elbow extension, the subject flexes the elbow at a constant speed to the maximum flexion angle and then extends it back to full extension at a constant speed. This process is repeated continuously at least ten times to ensure data stability.

[0029] The 3D motion capture system is connected to the data processing equipment via wired or wireless communication, transmitting the acquired spatiotemporal coordinate data of the marker points to the data processing equipment in real time. The data processing equipment can be a computer, workstation, or server equipped with dedicated analysis software, used to perform subsequent steps such as kinematic parameter calculation, feature extraction, and rehabilitation assessment. The raw data acquired by the 3D motion capture system is the time series of coordinates of each marker point in 3D space. Since data loss or anomalies may occur during the acquisition process due to marker point occlusion or system noise, this embodiment preprocesses the raw coordinate data. Preprocessing includes interpolation completion and filtering / denoising; any implementation method in the prior art can be used, and this embodiment does not specifically limit this approach.

[0030] Specifically, the parameter calculation steps include: constructing upper arm vectors and forearm vectors based on the spatiotemporal coordinates of the shoulder marker, elbow marker, and wrist marker; and generating elbow joint angle time series and elbow joint angular velocity time series based on the real-time spatial angle between the upper arm vector and the forearm vector.

[0031] In this step, the upper arm vector points from the shoulder marker to the elbow marker, and the forearm vector points from the elbow marker to the wrist marker. The elbow joint angle is the spatial angle between the upper arm vector and the forearm vector, which can be calculated using the vector dot product formula. The calculated elbow joint angle values ​​at all times constitute an elbow joint angle time series. The elbow joint angular velocity is obtained by performing a first-order difference on the elbow joint angle time series. Various methods can be used, such as forward difference, backward difference, or central difference. This embodiment preferably uses central difference to improve calculation accuracy. The calculated elbow joint angular velocity values ​​at all times constitute an elbow joint angular velocity time series.

[0032] Specifically, the feature extraction steps include: reconstructing the phase space of the elbow joint angle time series to generate the angle phase space trajectory, and calculating the angle fluctuation complexity index based on the geometric morphology features of the angle phase space trajectory; and performing symbolic dynamic analysis on the elbow joint angular velocity time series to generate symbolic angular velocity entropy values ​​based on the time distribution of angular velocity values.

[0033] In this step, phase space reconstruction is an important method for analyzing nonlinear dynamic systems. Its core idea is to map a one-dimensional time series into a high-dimensional phase space through time-delay embedding, thereby revealing the system's dynamic characteristics. This application's embodiment uses the time-delay embedding method to construct a two-dimensional phase space trajectory. The current angle value is used as the first dimension, and the angle value after a preset time step delay is used as the second dimension. The resulting two-dimensional point set constitutes the angle phase space trajectory. The delay time can be determined using any method in the prior art, such as the autocorrelation function method or the mutual information method. The distribution pattern of this phase space trajectory on the two-dimensional plane can intuitively reflect the hidden dynamic characteristics during angle changes, laying the foundation for subsequent feature extraction.

[0034] The angular fluctuation complexity index is used to quantify the smoothness characteristics of elbow joint movement. The core idea of ​​symbolic dynamics analysis is to convert continuous time series into discrete symbolic sequences, thereby extracting the underlying dynamic information. The symbolic entropy value of angular velocity is used to quantify the fluidity characteristics of elbow joint movement.

[0035] Specifically, the rehabilitation assessment steps include: inputting the angle fluctuation complexity index and the angular velocity symbolic entropy value into a pre-built rehabilitation quantitative assessment model, and using the rehabilitation quantitative assessment model to perform multi-dimensional fusion calculations on the angle fluctuation complexity index and the angular velocity symbolic entropy value to generate a comprehensive quantitative score for the subject's postoperative elbow joint rehabilitation.

[0036] In this step, the pre-constructed quantitative rehabilitation assessment model is a standard model built based on the motion data of a healthy control group. After inputting the subject's angular fluctuation complexity index and angular velocity symbolic entropy value into the model, the model generates a comprehensive quantitative score for postoperative elbow joint rehabilitation through multi-dimensional fusion calculation. This score can objectively quantify the subject's motor control function status.

[0037] Based on the above, this embodiment extracts two core features from three-dimensional motion capture data: the angular fluctuation complexity index and the symbolic entropy value of angular velocity. These features quantify the smoothness and fluidity of elbow joint movement, thereby generating a comprehensive rehabilitation score. Compared to existing technologies that rely solely on static angle measurements or simple curve comparisons, this embodiment can more comprehensively and objectively reflect the recovery status of the patient's motor control function, providing a scientific basis for clinical rehabilitation assessment.

[0038] To further clarify how to specifically calculate the angle fluctuation complexity index, in one embodiment, the angle fluctuation complexity index is calculated based on the geometric morphological characteristics of the angle phase space trajectory, including: Time delay embedding is performed on the elbow joint angle time series to construct a two-dimensional phase space trajectory with the current angle value as the first dimension and the angle value after a preset time step delay as the second dimension; Calculate the area covered by the trajectory points of the two-dimensional phase space trajectory, and use it as the trajectory extension feature; Calculate the dispersion of the distance distribution between each trajectory point and the trajectory center point on the two-dimensional phase space trajectory, and use it as a trajectory clustering feature; An angle fluctuation complexity index is generated based on a weighted combination of trajectory expansion features and trajectory clustering features.

[0039] In detail, let the elbow joint angle time series be... ,in The length of the time series. Indicates the first The elbow joint angle value at each sampling time. Let the delay time be... Then the two-dimensional phase space trajectory is formed by the point set Composition, denoted as point set ,in The total number of trajectory points. Indicates the first There are several trajectory points with coordinates as follows: ,in , Delay time The choice can be determined using any of the existing techniques, such as the autocorrelation function method or the mutual information method.

[0040] The area of ​​the region can be calculated using any method available in the art, such as calculating the area of ​​the smallest convex hull polygon of all trajectory points, or using the grid covering method to calculate the total area of ​​the grid cells covered by the trajectory points.

[0041] For trajectory clustering features First, calculate the center point of all trajectory points. Its coordinates are the mean of the coordinates of all trajectory points: , in and The first The x-coordinates and y-coordinates of each trajectory point are calculated. Then, the Euclidean distance from each trajectory point to the center point is calculated. : , in and The center point The x and y coordinates are used to obtain the distance sequence. The mean of this sequence is denoted as . Calculate the standard deviation of this distance sequence as a trajectory clustering feature: , The standard deviation reflects the degree of clustering of trajectory points around the center point: the smaller the standard deviation, the more tightly the trajectory points are clustered around the center point, and the more stable the motion; the larger the standard deviation, the more dispersed the trajectory points, and the less stable the motion.

[0042] The angular fluctuation complexity index includes the phase space trajectory area and the phase space trajectory dispersion, where the phase space trajectory area is the trajectory expansion feature. This is used to characterize the range of change in elbow joint angle; the phase space trajectory dispersion is the trajectory clustering feature. This is used to characterize the degree of trajectory aggregation of elbow joint angle changes.

[0043] Generate angular fluctuation complexity index The weighted combination can take the form of a linear weighted combination: , in and The preset weighting coefficients satisfy... The weighting coefficients can be determined based on clinical experience or optimized using experimental data; for example, they can be set to... , This allows trajectory clustering features to have a higher weight in the angular fluctuation complexity index, highlighting the importance of motion stability in rehabilitation assessment.

[0044] Based on the above, the geometric characteristics of the angular phase space trajectory are quantified into the phase space trajectory area and phase space trajectory dispersion, and an angular fluctuation complexity index is generated by weighted combination. The phase space trajectory area reflects the range of motion, and the phase space trajectory dispersion reflects the motion stability. The combination of the two can comprehensively characterize the quality of elbow joint movement, providing a quantitative basis for subsequent rehabilitation assessment.

[0045] To clarify how to specifically calculate the symbolic entropy value of angular velocity, in one embodiment, a symbolic dynamic analysis is performed on the time series of elbow joint angular velocity, and the symbolic entropy value of angular velocity is generated based on the time distribution of the angular velocity values, including: According to the preset angular velocity threshold, the angular velocity values ​​at each moment in the elbow joint angular velocity time series are converted into an angular velocity symbol sequence consisting of a first symbol and a second symbol. Angular velocity values ​​greater than or equal to the preset threshold are converted into the first symbol, and angular velocity values ​​less than the preset threshold are converted into the second symbol. The angular velocity symbol sequence is segmented using a sliding window of fixed length to generate multiple symbol subsequences; The frequency of occurrence of each symbol subsequence in multiple symbol subsequences is counted, and the symbolic entropy of angular velocity is calculated based on the uniformity of the frequency distribution.

[0046] In detail, let the time series of elbow joint angular velocity be... ,in The length of the time series. Indicates the first The elbow joint angular velocity values ​​at each sampling time. First, a preset angular velocity threshold needs to be established. This threshold can be determined based on the statistical characteristics of angular velocity in a healthy control group, such as the mean, median, or the sum of the mean and standard deviation of angular velocity in the healthy control group under the same movement. In the embodiments of this application, an empirical value can also be set based on the clinical experience of rehabilitation physicians. For example, for elbow flexion and extension movements, an empirical value can be set. .

[0047] Symbolic transformation based on a preset angular velocity threshold can be performed as follows: for each moment... angular velocity value ,like If , then convert it to the first symbol, for example, use "1" to represent it; if If the value is 0, it is converted into a second symbol, for example, represented by "0". After symbolization, a sequence of angular velocity symbols consisting of "0" and "1" is obtained. ,in And indicates the first The sign value at each moment.

[0048] The generation of symbol subsequences can be achieved by: assuming the sliding window length is... Typically, the value is 2, 3, or 4; in the embodiments of this application, it is used as... Let's take an example to illustrate. Starting from the first symbol in the sequence, we sequentially extract segments of length [length missing] using a sliding motion with a step size of 1. The symbolic subsequences were obtained in total. There are symbolic subsequences. Each symbolic subsequence has ___ symbolic subsequences. A possible pattern, when There are 8 possible patterns, such as “000”, “001”, “010”, “011”, “100”, “101”, “110”, and “111”.

[0049] The calculation of frequency of occurrence can be done as follows: Let the number of occurrences be... The number of times this pattern appears is The total number of subsequences is Then the first Frequency of occurrence of this pattern The frequencies of all modes satisfy .

[0050] For the symbolic entropy value of angular velocity The calculation in this application embodiment uses the Shannon entropy form: , The unit of this entropy value is bits. When When the value ranges from 0 to 3, and all patterns occur with equal probability, The entropy value reaches its maximum value. This indicates a rich variety of angular velocity change patterns and smooth motion; when certain patterns occur with extremely low or zero probability, the entropy value is small, indicating a single angular velocity change pattern and potential jerking or abnormalities in the motion. The closer the entropy value is to its maximum value... The more uniform the symbolic pattern distribution of the angular velocity time series, the better the motion smoothness; the smaller the entropy value, the more repetitive and stereotyped the angular velocity changes, and the worse the motion smoothness.

[0051] Based on the above, the continuous angular velocity time series is converted into a discrete symbolic sequence. By analyzing the uniformity of the pattern distribution of the symbolic subsequences, the smoothness characteristics of elbow joint movement are quantified. This method is robust to noise and can effectively capture the dynamic characteristics of angular velocity changes.

[0052] To clarify how to construct a quantitative rehabilitation assessment model, in one embodiment, the construction process of the quantitative rehabilitation assessment model includes: The spatiotemporal coordinates of the shoulder, elbow, and wrist landmarks of the healthy control group were acquired by a three-dimensional motion capture system during continuous cyclic flexion and extension movements. Based on the spatiotemporal coordinates of the shoulder, elbow, and wrist markers of the control group, the elbow joint angle time series and elbow joint angular velocity time series of the control group are generated. Based on the elbow joint angle time series and elbow joint angular velocity time series of the control group, the angle fluctuation complexity index and the symbolic entropy value of the control group are calculated. A multidimensional motion control feature set of the control group is generated, consisting of the angle fluctuation complexity index and the symbolic entropy value of the control group. The multidimensional control group's motor control feature set is fitted with a probability distribution to generate a standard motor control parameter set corresponding to continuous cyclic flexion and extension movements. The standard motor control parameter set includes the probability density function of each feature dimension in the multidimensional control group's motor control feature set and the confidence interval boundary determined based on the probability density function.

[0053] In detail, the selection of the healthy control group should follow strict inclusion and exclusion criteria. The sample size of the control group should be large enough, usually no less than 30 cases, to ensure the reliability of the statistical results. All control group members performed the same continuous cyclic flexion-extension movements as the subjects under the same conditions, and the spatiotemporal coordinates of their shoulder, elbow, and wrist landmarks were collected by the same three-dimensional motion capture system.

[0054] For each control group individual, the elbow joint angle time series and elbow joint angular velocity time series are generated according to the aforementioned method, and the control group angle fluctuation complexity index and control group angular velocity symbolic entropy value are calculated. Let there be a total of... Named control individuals, then the first The angular fluctuation complexity of individual references is denoted as... The symbolic entropy value of angular velocity is denoted as The eigenvalues ​​of all control individuals constitute a multidimensional control group motor control feature set. .

[0055] Probability distribution fitting is performed on the motion control feature set of the multidimensional control group. First, distribution fitting is performed on the angular fluctuation complexity index and the symbolic entropy value of angular velocity. Commonly used distribution models include normal distribution, log-normal distribution, and Gamma distribution. The goodness of fit can be tested using methods such as the Kolmogorov-Smirnov test and the Shapiro-Wilk test to select the optimal distribution model. The above probability distribution fitting methods are all mature techniques in the field of statistics, and this application does not specifically limit them. For the angular fluctuation complexity index, its probability density function is fitted. ,in The value of the angular fluctuation complexity index is represented; for the symbolic entropy value of angular velocity, its probability density function is obtained by fitting. ,in The value represents the symbolic entropy of the angular velocity.

[0056] Based on the probability density function obtained from the fitting, the confidence interval boundaries for each feature dimension are determined. For example, with a significance level of 0.05, a two-sided 95% confidence interval can be calculated; for the angular variability complexity index, the lower bound of the confidence interval is... and upper limit Corresponding to probability density functions The 2.5% and 97.5% quantiles of the cumulative distribution function; the lower bound of the confidence interval for the symbolic entropy value of angular velocity. and upper limit Corresponding to probability density functions The 2.5% and 97.5% quantiles of the cumulative distribution function. These confidence interval boundaries constitute an important part of the standard motion control parameter set.

[0057] Finally, the probability density functions and confidence interval boundaries of each feature dimension together constitute the standard set of motor control parameters corresponding to continuous cyclic flexion-extension movements. This parameter set serves as a reference benchmark for subsequent rehabilitation assessment of subjects, representing the distribution range of normal motor control characteristics in healthy individuals under the same movements.

[0058] To clarify how to generate a comprehensive quantitative rehabilitation score for a subject based on a constructed set of standard motor control parameters, in one embodiment, the generation of a comprehensive quantitative rehabilitation score for the subject's elbow joint after surgery includes: Based on the quantile positions of the angle fluctuation complexity index and the symbolic entropy value of angular velocity in the probability density function of the standard motion control parameter set, determine the index quantile matching degree corresponding to the angle fluctuation complexity index and the entropy value quantile matching degree corresponding to the symbolic entropy value of angular velocity. A basic score is generated based on the weighted sum of the indicator quantile matching degree and the entropy quantile matching degree. The cumulative number of times the statistical angle fluctuation complexity index and the symbolic entropy value of angular velocity cross the confidence interval boundary per unit time are used to generate a stability decay coefficient based on the relationship between the cumulative number and the preset number threshold. A comprehensive rehabilitation score is generated based on a combination of the baseline score and the stability decay coefficient.

[0059] Furthermore, based on the combination of the baseline score and the stability decay coefficient, a comprehensive quantitative rehabilitation score is generated, including: When the stability decay coefficient is less than or equal to the preset decay threshold, the baseline score will be used as the comprehensive quantitative rehabilitation score. When the stability decay coefficient is greater than the preset decay threshold, the basic score is decayed according to the ratio of the difference between the stability decay coefficient and the preset decay threshold, and the score after decay is used as the comprehensive rehabilitation quantitative score.

[0060] In detail, the complexity index of the subject's angular fluctuation is denoted as a value. Search for its probability density function as an indicator of angular fluctuation complexity in the standard motion control parameter set. The quantile position of the middle ,Right now satisfy: , quantiles The value range is between 0 and 1. The closer the value is to 0.5, the closer the test result is to the central tendency of healthy individuals. A value closer to 0 or 1 indicates that the subject's indicator deviates from the normal range. The quantile fit of the indicator is calculated based on quantiles. : , The matching score ranges from 0 to 1, with a higher value indicating a higher degree of matching with healthy individuals.

[0061] Similarly, for the symbolic entropy value of the subject's angular velocity, let its value be denoted as . Search for its probability density function of symbolic entropy value at angular velocity in the standard motion control parameter set. The quantile position of the middle ,Right now satisfy: , Calculate the entropy quantile matching degree .

[0062] A basic score is generated based on the weighted sum of the indicator quantile matching degree and the entropy quantile matching degree. : , in and The preset weighting coefficients satisfy... The weighting coefficients can be determined based on clinical experience, for example, by taking... , This indicates that smoothness and fluency are equally important in the basic score.

[0063] While generating the baseline score, it is also necessary to assess the stability of the subject's movement, i.e., whether there are frequent deviations from the normal range during the movement. This involves counting the cumulative number of times the subject's angular fluctuation complexity index and angular velocity symbolic entropy value cross the confidence interval boundary per unit time throughout the entire movement process. Specifically, the movement process is divided into continuous, fixed-length time windows, each with a length of [missing information]. seconds, for example, take Seconds. Within each time window, monitor whether the angle fluctuation complexity index crosses its confidence interval. The boundary, and whether the symbolic entropy value of angular velocity crosses its confidence interval. The boundary of the interval. Crossing is defined as either moving from inside the interval to outside the interval, or from outside the interval to inside the interval. Count the total number of crossing events within all windows during the entire movement. Then divide by the total exercise time. (Unit: seconds) This gives the cumulative number of times per unit of time. The unit is times per second.

[0064] Based on cumulative number of times Compared with the preset number of thresholds The magnitude relationship generates the stability decay coefficient Preset number of times threshold It can be set based on clinical experience, for example, taking... times / second. The stability decay coefficient is calculated as follows: , in This is a preset decay rate parameter, with a value ranging from 0 to 1. The larger the value, the more severe the decay.

[0065] A comprehensive rehabilitation score is generated based on a combination of the baseline score and the stability decay coefficient. The embodiments of this application use multiplication for combination operations: , When the stability decay coefficient is less than or equal to the preset decay threshold, that is... hour The baseline score is directly used as the comprehensive quantitative score for rehabilitation; when the stability decay coefficient is greater than the preset decay threshold, i.e. At that time, the base score is attenuated according to the ratio of the difference between the stability attenuation coefficient and the preset attenuation threshold, so that the score decreases as stability deteriorates.

[0066] Based on the above, a score decay for movements with poor stability was achieved, and the degree of decay was proportional to the degree of stability deterioration. This segmented processing method ensures that the score is not affected within the normal stability range, while also allowing for reasonable penalties when stability is abnormal, so that the final quantitative comprehensive rehabilitation score can more accurately reflect the subject's true functional status.

[0067] It should be understood that, although Figure 2 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 2 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. 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 some of the sub-steps or stages of other steps.

[0068] Secondly, a quantitative assessment system for postoperative rehabilitation of elbow joint based on three-dimensional motion capture is provided. The system includes a data acquisition module, a parameter calculation module, a feature extraction module, and a rehabilitation assessment module.

[0069] The data acquisition module is configured to acquire the spatiotemporal coordinates of the shoulder, elbow, and wrist landmarks of the affected upper limb of the subject when performing continuous cyclic flexion and extension movements, as collected by the three-dimensional motion capture system.

[0070] The parameter calculation module is configured to construct upper arm vectors and forearm vectors based on the spatiotemporal coordinates of shoulder markers, elbow markers, and wrist markers, and generate elbow joint angle time series and elbow joint angular velocity time series based on the real-time spatial angle between the upper arm vector and the forearm vector. The feature extraction module is configured to reconstruct the phase space of the elbow joint angle time series, generate the angle phase space trajectory, and calculate the angle fluctuation complexity index based on the geometric morphology features of the angle phase space trajectory; and to perform symbolic dynamic analysis on the elbow joint angular velocity time series, and generate symbolic entropy values ​​of angular velocity based on the time distribution of angular velocity values. The rehabilitation assessment module is configured to input the angle fluctuation complexity index and the angular velocity symbolic entropy value into a pre-built rehabilitation quantitative assessment model. The rehabilitation quantitative assessment model performs multi-dimensional fusion calculations on the angle fluctuation complexity index and the angular velocity symbolic entropy value to generate a comprehensive quantitative score for the subject's postoperative elbow joint rehabilitation.

[0071] The aforementioned modules can be integrated into the same data processing device or distributed and work collaboratively through network communication. The specific hardware implementation of each module can adopt any of the existing technologies such as general-purpose processors, digital signal processors, application-specific integrated circuits, and field-programmable gate arrays; this application embodiment does not limit this.

[0072] The system described above can execute the postoperative elbow joint rehabilitation quantitative assessment method based on three-dimensional motion capture provided in the embodiments of this application, realizing fully automated processing from motion data acquisition to the generation of comprehensive rehabilitation scores, and providing objective quantitative tool support for clinical rehabilitation assessment.

[0073] In one embodiment, the feature extraction module includes an index calculation unit.

[0074] The index calculation unit is used to embed the elbow joint angle time series with time delay, and construct a two-dimensional phase space trajectory with the current angle value as the first dimension and the angle value after a preset time step delay as the second dimension; it is used to calculate the area covered by the trajectory points of the two-dimensional phase space trajectory as the trajectory expansion feature; it is used to calculate the dispersion of the distance distribution between each trajectory point on the two-dimensional phase space trajectory and the trajectory center point as the trajectory clustering feature; and it is used to generate an angle fluctuation complexity index based on the weighted combination of the trajectory expansion feature and the trajectory clustering feature.

[0075] Furthermore, the angular fluctuation complexity index includes the phase space trajectory area and the phase space trajectory dispersion, where the phase space trajectory area is used to characterize the range of elbow joint angle changes, and the phase space trajectory dispersion is used to characterize the degree of trajectory clustering of elbow joint angle changes.

[0076] In one embodiment, the feature extraction module includes an entropy generation unit.

[0077] The entropy generation unit is used to convert the angular velocity values ​​at each moment in the elbow joint angular velocity time series into an angular velocity symbol sequence composed of a first symbol and a second symbol according to a preset angular velocity threshold. Angular velocity values ​​greater than or equal to the preset threshold are converted into the first symbol, and angular velocity values ​​less than the preset threshold are converted into the second symbol. The unit is also used to divide the angular velocity symbol sequence with a sliding window of fixed length to generate multiple symbol subsequences. Furthermore, the unit is used to count the occurrence frequency of each symbol subsequence in the multiple symbol subsequences and calculate the angular velocity symbol entropy value based on the uniformity of the occurrence frequency distribution.

[0078] In one embodiment, the rehabilitation assessment module includes a model building unit.

[0079] The model building unit is used to acquire the spatiotemporal coordinates of the shoulder, elbow, and wrist landmarks of the healthy control group when performing continuous cyclic flexion-extension movements, collected by a 3D motion capture system. Based on these coordinates, it generates elbow joint angle and angular velocity time series for the control group. It then calculates the angle fluctuation complexity index and the symbolic entropy value of the angular velocity, generating a multidimensional control group motion control feature set composed of these two parameters. Finally, it performs probability distribution fitting on the multidimensional control group motion control feature set to generate a standard motion control parameter set corresponding to the continuous cyclic flexion-extension movements. This standard parameter set includes the probability density function of each feature dimension in the multidimensional control group motion control feature set and the confidence interval boundary determined based on the probability density function, ultimately yielding a quantitative rehabilitation assessment model.

[0080] In one embodiment, the rehabilitation assessment module includes a score generation unit.

[0081] The scoring generation unit is used to determine the quantile matching degree of the angular fluctuation complexity index and the entropy quantile matching degree of the entropy value corresponding to the angular velocity symbolic entropy value based on the quantile positions of the angular fluctuation complexity index and the angular velocity symbolic entropy value in the probability density function of the standard motion control parameter set; it is used to generate a basic score based on the weighted sum of the quantile matching degree of the index and the entropy quantile matching degree of the entropy value; it is used to count the cumulative number of times the angular fluctuation complexity index and the angular velocity symbolic entropy value cross the confidence interval boundary per unit time, and generate a stability decay coefficient based on the relationship between the cumulative number and the preset number threshold; and it is used to generate a comprehensive rehabilitation quantitative score based on the combination of the basic score and the stability decay coefficient.

[0082] Furthermore, the scoring generation unit includes a combination operation subunit.

[0083] The combined operation subunit is used to use the basic score as the comprehensive rehabilitation score when the stability attenuation coefficient is less than or equal to the preset attenuation threshold; and to attenuate the basic score according to the ratio of the difference between the stability attenuation coefficient and the preset attenuation threshold when the stability attenuation coefficient is greater than the preset attenuation threshold, and use the attenuated score as the comprehensive rehabilitation score.

[0084] In addition, it should be noted that the specific limitations of the system for implementing a quantitative assessment method for postoperative rehabilitation of the elbow joint based on three-dimensional motion capture can be found in the limitations of the quantitative assessment method for postoperative rehabilitation of the elbow joint based on three-dimensional motion capture mentioned above, and will not be repeated here.

[0085] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a method. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0086] Those skilled in the art will understand that Figure 4The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0087] Thirdly, a computer device is provided, including a memory and a processor. The memory is communicatively connected to the processor, and the memory stores a computer program executable by the processor. When the computer program is executed by the processor, it implements the aforementioned method for quantitative assessment of elbow joint postoperative rehabilitation based on three-dimensional motion capture. Furthermore, it should be noted that the specific limitations of this computer device in implementing the method for quantitative assessment of elbow joint postoperative rehabilitation based on three-dimensional motion capture can be found in the limitations of the method described above, and will not be repeated here.

[0088] Fourthly, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it implements the aforementioned method for quantitative assessment of elbow joint postoperative rehabilitation based on three-dimensional motion capture. Furthermore, it should be noted that the specific limitations of this computer-readable storage medium in implementing the method for quantitative assessment of elbow joint postoperative rehabilitation based on three-dimensional motion capture can be found in the limitations of the method described above, and will not be repeated here.

[0089] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0090] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.

[0091] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A quantitative assessment method for postoperative rehabilitation of the elbow joint based on three-dimensional motion capture, characterized in that, The method includes: The spatiotemporal coordinates of the shoulder, elbow, and wrist landmarks of the affected upper limb were collected using a three-dimensional motion capture system when the subject performed continuous cyclic flexion and extension movements. Based on the spatiotemporal coordinates of the shoulder marker, the elbow marker, and the wrist marker, an upper arm vector and a forearm vector are constructed. Based on the real-time spatial angle between the upper arm vector and the forearm vector, an elbow joint angle time series and an elbow joint angular velocity time series are generated. The elbow joint angle time series is reconstructed in phase space to generate an angle phase space trajectory, and the angle fluctuation complexity index is calculated based on the geometric morphology characteristics of the angle phase space trajectory; and the elbow joint angular velocity time series is subjected to symbolic dynamic analysis to generate a symbolic entropy value of angular velocity based on the time distribution of angular velocity values. The angle fluctuation complexity index and the angular velocity symbolic entropy value are input into a pre-constructed rehabilitation quantitative assessment model. The rehabilitation quantitative assessment model performs multi-dimensional fusion calculation on the angle fluctuation complexity index and the angular velocity symbolic entropy value to generate a comprehensive quantitative score for the subject's elbow joint postoperative rehabilitation.

2. The method for quantitative assessment of elbow joint postoperative rehabilitation based on three-dimensional motion capture according to claim 1, characterized in that, The calculation of the angle fluctuation complexity index based on the geometric morphological characteristics of the angle phase space trajectory includes: The elbow joint angle time series is embedded with a time delay to construct a two-dimensional phase space trajectory with the current angle value as the first dimension and the angle value after a preset time step delay as the second dimension. Calculate the area covered by the trajectory points of the two-dimensional phase space trajectory, and use it as the trajectory extension feature; The dispersion of the distance distribution between each trajectory point and the trajectory center point on the two-dimensional phase space trajectory is calculated as a trajectory clustering feature. The angle fluctuation complexity index is generated based on a weighted combination of the trajectory expansion features and the trajectory aggregation features.

3. The method for quantitative assessment of elbow joint postoperative rehabilitation based on three-dimensional motion capture according to claim 2, characterized in that, The angular fluctuation complexity index includes the phase space trajectory area and the phase space trajectory dispersion, wherein the phase space trajectory area is used to characterize the range of elbow joint angle changes, and the phase space trajectory dispersion is used to characterize the degree of trajectory clustering of elbow joint angle changes.

4. The method for quantitative assessment of elbow joint postoperative rehabilitation based on three-dimensional motion capture according to claim 1, characterized in that, The symbolic dynamic analysis of the elbow joint angular velocity time series, generating symbolic entropy values ​​of angular velocity based on the time distribution of angular velocity values, includes: According to a preset angular velocity threshold, the angular velocity values ​​at each moment in the elbow joint angular velocity time series are converted into an angular velocity symbol sequence composed of a first symbol and a second symbol, wherein angular velocity values ​​greater than or equal to the preset threshold are converted into the first symbol, and angular velocity values ​​less than the preset threshold are converted into the second symbol. The angular velocity symbol sequence is segmented using a sliding window of fixed length to generate multiple symbol subsequences; The frequency of occurrence of each symbol subsequence in the plurality of symbol subsequences is statistically analyzed, and the angular velocity symbolization entropy value is calculated based on the uniformity of the distribution of the frequency of occurrence.

5. The method for quantitative assessment of elbow joint postoperative rehabilitation based on three-dimensional motion capture according to claim 1, characterized in that, The process of constructing the quantitative assessment model for rehabilitation includes: The spatiotemporal coordinates of the shoulder markers, elbow markers, and wrist markers of the healthy control group were acquired by the three-dimensional motion capture system when performing the continuous cyclic flexion and extension movements. Based on the spatiotemporal coordinates of the shoulder markers, elbow markers, and wrist markers of the control group, a time series of elbow joint angles and a time series of elbow joint angular velocities of the control group are generated. Based on the time series of elbow joint angles and the time series of elbow joint angular velocities of the control group, an angle fluctuation complexity index and a symbolic entropy value of angular velocity of the control group are calculated. A multidimensional motion control feature set of the control group is generated, consisting of the angle fluctuation complexity index and the symbolic entropy value of angular velocity of the control group. The multidimensional control group's motor control feature set is fitted with a probability distribution to generate a standard motor control parameter set corresponding to the continuous cyclic flexion-extension movement. The standard motor control parameter set includes the probability density function of each feature dimension in the multidimensional control group's motor control feature set and the confidence interval boundary determined based on the probability density function.

6. The method for quantitative assessment of elbow joint postoperative rehabilitation based on three-dimensional motion capture according to claim 5, characterized in that, The generation of the subject's post-operative elbow joint rehabilitation quantitative comprehensive score includes: Based on the quantile positions of the angle fluctuation complexity index and the symbolic entropy value of the angular velocity in the probability density function of the standard motion control parameter set, determine the index quantile matching degree corresponding to the angle fluctuation complexity index and the entropy value quantile matching degree corresponding to the symbolic entropy value of the angular velocity; A basic score is generated based on the weighted sum of the quantile matching degree of the indicator and the quantile matching degree of the entropy value; The cumulative number of times the angle fluctuation complexity index and the symbolic entropy value of the angular velocity cross the boundary of the confidence interval per unit time is counted, and a stability decay coefficient is generated based on the relationship between the cumulative number and the preset number threshold. The comprehensive rehabilitation score is generated by combining the baseline score and the stability decay coefficient.

7. The method for quantitative assessment of elbow joint postoperative rehabilitation based on three-dimensional motion capture according to claim 6, characterized in that, The step of generating the comprehensive rehabilitation score based on the combination of the baseline score and the stability decay coefficient includes: When the stability decay coefficient is less than or equal to the preset decay threshold, the basic score is used as the comprehensive rehabilitation score. When the stability decay coefficient is greater than the preset decay threshold, the basic score is decayed according to the ratio of the difference between the stability decay coefficient and the preset decay threshold, and the score after decay is used as the comprehensive rehabilitation quantitative score.

8. A quantitative assessment system for postoperative rehabilitation of the elbow joint based on three-dimensional motion capture, characterized in that, The system includes: The data acquisition module is configured to acquire the spatiotemporal coordinates of the shoulder, elbow, and wrist landmarks of the affected upper limb of the subject when performing continuous cyclic flexion and extension movements, as collected by the three-dimensional motion capture system. The parameter calculation module is configured to construct an upper arm vector and a forearm vector based on the spatiotemporal coordinates of the shoulder marker, the elbow marker, and the wrist marker, and to generate an elbow joint angle time series and an elbow joint angular velocity time series based on the real-time spatial angle between the upper arm vector and the forearm vector. The feature extraction module is configured to reconstruct the phase space of the elbow joint angle time series, generate the angle phase space trajectory, and calculate the angle fluctuation complexity index based on the geometric morphology features of the angle phase space trajectory; and to perform symbolic dynamic analysis on the elbow joint angular velocity time series, and generate symbolic entropy values ​​of angular velocity based on the time distribution of angular velocity values. The rehabilitation assessment module is configured to input the angle fluctuation complexity index and the angular velocity symbolic entropy value into a pre-built rehabilitation quantitative assessment model, and to perform multi-dimensional fusion calculation on the angle fluctuation complexity index and the angular velocity symbolic entropy value through the rehabilitation quantitative assessment model to generate a comprehensive quantitative score for the subject's elbow joint postoperative rehabilitation.

9. A computer device comprising a memory and a processor, the memory being communicatively connected to the processor, and the memory storing a computer program executable by the processor, characterized in that, When the computer program is executed by the processor, it implements the method for quantitative assessment of postoperative elbow joint rehabilitation based on three-dimensional motion capture as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method for quantitative assessment of postoperative elbow joint rehabilitation based on three-dimensional motion capture as described in any one of claims 1 to 7.

Images