Parkinson's Disease Gait Impairment Assessment Model, Method and Storage Medium

Abstract

The present invention relates to the technical field of medical image processing, and particularly to establishing a gait impairment assessment model, method and storage medium for Parkinson's disease. The method includes the following steps: continuously monitoring the gait images of Parkinson's disease patients; when a gait continuity interruption of the gait image is detected, it is determined as a gait freezing event, and the freezing event characteristics, the freezing occurrence time period and the freezing duration of the gait freezing event are recorded; determining gait feature parameters based on the gait images; extracting the spatio-temporal gait feature parameters of the gait feature parameters, and constructing a gait feature curve according to the spatio-temporal gait feature parameters; identifying the precursor attributes of the freezing event characteristics according to the gait feature curve to obtain the freezing event precursor attributes. The present invention realizes the gait monitoring of Parkinson's disease patients through data processing technology and image processing technology, and identifies the gait freezing characteristics, so as to improve the accuracy of the gait impairment assessment for Parkinson's disease and shorten the time used in the impairment assessment process.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing, and particularly to a method and storage medium for establishing a gait impairment assessment model for Parkinson's disease. Background Art

[0002] In the early stage, the gait assessment of Parkinson's disease mainly relied on the experience of clinicians and the subjective descriptions of patients. Doctors judged the degree of gait impairment by observing the walking postures and gait characteristics of patients. This method has a large degree of subjectivity, lacks a unified quantitative standard, and is difficult to accurately evaluate the changes in the condition. As gait analysis technology was gradually introduced into the assessment of Parkinson's disease, by collecting parameters in the walking cycle, gait analysis could quantify gait abnormalities. Most of the technologies at this stage were based on laboratory environments and used devices such as pressure sensors and optical motion capture systems. However, existing technologies cannot accurately identify the specific characteristics and duration of gait interruption when detecting gait freezing events in Parkinson's disease patients. Moreover, existing gait analysis methods only focus on single gait parameters and lack comprehensive analysis of spatio-temporal characteristic parameters of gait, making it difficult to monitor gait characteristics, resulting in low accuracy in assessing gait impairment in Parkinson's disease. Summary of the Invention

[0003] Based on this, it is necessary to provide a method and storage medium for establishing a gait impairment assessment model for Parkinson's disease to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for establishing a gait impairment assessment for Parkinson's disease includes the following steps:

[0005] Step S1: Continuously monitor the gait images of Parkinson's disease patients; when a gait continuity interruption in the gait image is detected, it is determined as a gait freezing event, and the freezing event characteristics, the freezing occurrence time period, and the freezing duration of the gait freezing event are recorded.

[0006] Step S2: Determine gait characteristic parameters based on the gait images; extract the spatio-temporal characteristic parameters of the gait characteristic parameters, and construct a gait characteristic curve according to the spatio-temporal characteristic parameters of the gait; identify the precursor attributes of the freezing event characteristics according to the gait characteristic curve to obtain the freezing event precursor attributes.

[0007] Step S3: Divide the freezing event precursor attributes into gait gradual change types; perform gait freezing cycle detection on the gait gradual change types according to the freezing occurrence time period to generate a gait freezing cycle; perform freezing cumulative frequency quantization on the gait freezing cycle based on the freezing duration to obtain a gait freezing index.

[0008] Step S4: Determine the gait change trend based on the freezing cycle data and the gait freezing index, and evaluate the degree of gait impairment in Parkinson's disease for the gait change trend to generate a gait impairment assessment report.

[0009] The present invention monitors the gait of Parkinson's disease patients in real time through a high-resolution image acquisition device, ensuring that a complete sequence of gait images can be captured at any point in time, continuously recording the walking process of the patients, and providing a comprehensive data basis for subsequent analysis; analyzes the gait images based on image processing algorithms, and automatically determines a gait freezing event when a gait continuity interruption is detected. At the same time, the characteristics of the freezing event are recorded, including the time period when the freezing occurs, the duration of the freezing, and the morphological characteristics of the freezing event, ensuring the accuracy and integrity of the data and avoiding errors caused by manual intervention. Gait spatio-temporal characteristic parameters are extracted from the gait images, including key parameters such as step length, step width, walking speed, and gait cycle. These parameters are calculated through image analysis algorithms, ensuring the objectivity and repeatability of the data. Based on the extracted gait spatio-temporal characteristic parameters, a gait characteristic curve is constructed, with time as the horizontal axis and the gait characteristic parameters as the vertical axis, which can intuitively reflect the change trend of gait parameters over time. And through this curve processing, the system can capture the dynamic process of gait changes; by analyzing the gait characteristic curve, the characteristic changes before the occurrence of the freezing event are identified, that is, the precursor attributes of the freezing event. This identification process is based on the morphological analysis of the curve and the change trend of the parameters, and can accurately locate the precursor characteristics of the freezing event. The precursor attributes of the freezing event are divided into different gait gradual change types. This division is based on the morphological characteristics and parameter change rules of the gait characteristic curve, and can classify complex gait changes; and according to the time period when the freezing occurs, the gait gradual change types are periodically detected. By analyzing the periodic changes of the gait characteristic curve, the periodic pattern of gait freezing can be accurately identified, thus revealing the regularity of the gait freezing event; a quantitative analysis of the gait freezing cycle is carried out based on the duration of the freezing, and it is obtained by calculating the weighted sum of the cumulative frequency and the duration of the freezing event, which can comprehensively reflect the severity of gait freezing and provide a unified quantitative standard for the evaluation of the degree of gait impairment. Based on the freezing cycle data and the gait freezing index, the trend of gait changes is analyzed through a mathematical model, which can comprehensively consider the regularity of the freezing cycle and the change trend of the freezing index, so as to accurately judge the overall situation of gait impairment; according to the trend of gait changes, a quantitative evaluation of the degree of gait impairment is carried out. This evaluation process is based on a preset quantitative standard, and by calculating the difference between the gait freezing index and the normal gait parameters, an objective and quantitative evaluation result can be provided; a detailed gait impairment evaluation report is generated according to the evaluation result. The report includes a detailed record of the freezing event, the gait characteristic curve, the analysis result of the freezing cycle, and the quantitative evaluation of the degree of gait impairment. The report is presented in the form of charts and data, which can intuitively display the detailed situation of gait changes and provide comprehensive data support for relevant research. Therefore, the present invention realizes the gait monitoring of Parkinson's disease patients through data processing technology and image processing technology, and identifies the gait freezing characteristics, so as to improve the accuracy of the evaluation of Parkinson's disease gait impairment and shorten the time used in the impairment evaluation process.

[0010] Preferably, step S1 includes the following steps:

[0011] Step S11: Set the frame rate of the binocular camera to 40 - 60 frames per second, the resolution to 1920×1080 pixels, and the angle between the binocular camera and the patient's walking path to 45°;

[0012] Step S12: Collect the complete cycle of each patient's walk, including the starting gait, the intermediate gait, and the ending gait, and the duration of each collection is 3 minutes;

[0013] Step S13: Activate the automatic tracking function of the binocular camera to continuously monitor the walking path, the number of walking steps, the walking speed, and the walking actions of the Parkinson's disease patient to obtain gait images;

[0014] Step S14: Record the number of times the patient's pace swings in the gait image, and mark the situation of zero times in two consecutive cycles; Determine the gait interruption points for the situation of zero times in two consecutive cycles to obtain gait continuity interruption data;

[0015] Step S15: Make a gait freezing judgment on the gait image according to the gait continuity interruption data to obtain gait freezing events, and record the freezing event characteristics, the freezing occurrence time period, and the freezing duration of the gait freezing events.

[0016] The present invention sets the frame rate of the binocular camera to 40 - 60 frames per second, the resolution to 1920×1080 pixels, and the angle between the binocular camera and the patient's walking path to 45°; setting the frame rate of the binocular camera to 40 - 60 frames per second and the resolution to 1920×1080 pixels can ensure clear and continuous image data capture during gait monitoring, avoiding image blurring and information loss caused by insufficient frame rate or low resolution. Setting the angle between the binocular camera and the patient's walking path to 45° can effectively capture the side profile and dynamic changes of the patient's gait, while reducing occlusion and distortion caused by perspective problems, ensuring accurate extraction of gait features; collecting the complete cycle of each patient's walk, including the starting gait, intermediate gait, and ending gait, can comprehensively reflect the patient's gait characteristics at different stages, avoiding analysis deviation caused by fragmented collection; each collection lasts for 3 minutes to ensure sufficient gait data is collected, while avoiding data insufficiency or redundancy caused by too short or too long collection time; starting the automatic tracking function of the binocular camera can real-time monitor the patient's walking path, steps, speed, and movements, ensuring clear gait images are always captured during the patient's walk, avoiding errors caused by manual adjustment. Monitoring the walking path, steps, speed, and movements simultaneously can provide a rich data basis for subsequent gait analysis, supporting the accurate identification of gait freezing events; recording the number of swings of the patient's gait in the gait image can quantify the change in the patient's gait rhythm, providing key data for identifying gait freezing events, marking the zero - number situation in two consecutive cycles as a gait interruption point can accurately locate the occurrence position of the gait freezing event, ensuring the accuracy of subsequent analysis; making a gait freezing judgment based on the gait continuity interruption data can accurately identify gait freezing events, avoiding errors caused by subjective judgment; recording the freezing event characteristics, freezing occurrence time period, and freezing duration of the gait freezing event can provide comprehensive and accurate data support for subsequent gait impairment assessment.

[0017] The determining of gait feature parameters based on the gait image includes:

[0018] Dividing the gait image into multiple consecutive frame sequences, where each frame sequence corresponds to a gait cycle;

[0019] In each frame sequence, extracting the foot joints, knee joints, and ankle joints to obtain human joint point information; calculating the displacement time change of the human joint point information in adjacent frames to generate a gait motion cycle;

[0020] Calculating the distance between the foot joint and the contact point in two consecutive gait motion cycles to obtain step - length data; measuring the lateral distance between the left and right foot joints and the contact point to obtain step - width data;

[0021] Calculate the gait speed by using the step length data and the gait motion cycle; determine the gait symmetry based on the gait speed and the step width data for the gait motion cycle;

[0022] Calculate the flexion and extension phase angles of the knee joint and the ankle joint in two consecutive gait motion cycles, and map the flexion and extension phase angles to the flexion and extension dispersion to obtain the joint flexion and extension dispersion;

[0023] Combine the gait motion cycle, the step length data, the step width data, the gait speed, the gait symmetry, and the joint flexion and extension dispersion into gait feature parameters.

[0024] By dividing the gait image into multiple consecutive frame sequences and making each frame sequence correspond to a gait cycle, the present invention can ensure that the analysis of the gait is based on a complete gait action unit, providing a clear time division for subsequent feature extraction;

[0025] Extract the information of the foot joint, the knee joint, and the ankle joint in each frame sequence, which can accurately locate the movement trajectories of the key parts of the human body and provide basic data for the quantitative analysis of gait features; by calculating the displacement time change of the human joint points in adjacent frames, it can accurately reflect the dynamic process of joint movement and provide a time reference for the subsequent quantitative analysis of gait features; calculate the distance between the foot joint and the contact point in two consecutive gait motion cycles, which can directly obtain the step length data and provide a key parameter for the quantitative analysis of gait features; by measuring the lateral distance between the left and right foot joints and the contact point, it can accurately obtain the step width data and provide an important lateral parameter for the quantitative analysis of gait features; combine the step length data with the gait motion cycle to calculate the gait speed, which can directly reflect the walking speed of the patient and provide a speed parameter for the quantitative analysis of gait features; analyze the gait motion cycle based on the gait speed and the step width data to determine the gait symmetry, providing a quantitative basis for evaluating the coordination and balance of the gait; by calculating the flexion and extension phase angles of the knee joint and the ankle joint in two consecutive gait motion cycles and mapping them to the flexion and extension dispersion, it can quantify the coordination and consistency of joint movement and provide an important parameter for the comprehensive analysis of gait features; combine the gait motion cycle, the step length data, the step width data, the gait speed, the gait symmetry, and the joint flexion and extension dispersion into gait feature parameters, which can comprehensively reflect the dynamic characteristics of the gait and provide comprehensive quantitative data for the subsequent gait impairment assessment.

[0026] Extract the spatio-temporal feature parameters of the gait for the gait feature parameters, and construct a gait feature curve according to the spatio-temporal feature parameters of the gait, including:

[0027] Extract the cycle time information of the gait feature parameters, and divide the cycle time information into a time period sequence; parameterize the time period sequence to obtain the time period sequence parameters;

[0028] Perform gait space feature recognition on gait feature parameters based on the time period sequence parameters, and perform feature parameter quantization on the gait space features to obtain the time period sequence parameters;

[0029] Arrange the time period sequence parameters in chronological order to form time-ordered data;

[0030] Use the time-ordered data as the horizontal axis and the time period sequence parameters as the vertical axis to construct an initial gait feature curve;

[0031] Perform curve smoothness processing on the initial gait feature curve to generate a gait feature curve.

[0032] By extracting the cycle time information of the gait feature parameters and dividing it into a time period sequence, the present invention can subdivide the time dimension of the gait data, providing a clear time framework for subsequent parameterization processing; performing parameterization processing on the time period sequence can convert time information into a quantifiable data form, providing basic data support for further analyzing gait features; performing spatial feature recognition on the gait feature parameters based on the time period sequence parameters and performing quantization processing can convert the spatial features of the gait into specific numerical parameters; arranging the time period sequence parameters in chronological order to form time-ordered data can ensure the time coherence of the data, providing an ordered data basis for constructing the gait feature curve; using the time-ordered data as the horizontal axis and the time period sequence parameters as the vertical axis to construct an initial gait feature curve; constructing an initial gait feature curve with the time-ordered data as the horizontal axis and the time period sequence parameters as the vertical axis can intuitively display the change trend of the gait features over time, providing a visualization basis for subsequent curve processing. Performing smoothness processing on the initial gait feature curve to generate a smooth gait feature curve can remove noise and abnormal fluctuations in the curve.

[0033] The precursor attributes for identifying the frozen event features according to the gait feature curve include:

[0034] On the gait feature curve, mark the time point when the gait speed drops below 0.5 m / s as the starting point of the speed freeze event; calculate the change rate of the gait speed within 3 seconds before and after the marked point based on the starting point of the speed freeze event. If the change rate is less than -0.2 m / s², it is determined as a speed precursor feature;

[0035] On the gait feature curve, mark the time point when the gait symmetry index drops below 0.8 as the starting point of the symmetry freeze event; compare the change in gait symmetry within 5 seconds before and after the marked point based on the starting point of the symmetry freeze event. If the symmetry change exceeds 0.2, record the time interval of the gait symmetry change. If the interval is less than 1 second, it is determined as a symmetry precursor feature;

[0036] On the gait feature curve, mark the time point when the step length shortens to less than 68 cm as the starting point of the step length freezing event; according to the starting point of the step length freezing event, compare the change in step length within 3 seconds before and after the marked point. If the step length shortens by more than 5 cm, it is considered a step length precursor feature;

[0037] On the gait feature curve, mark the time point when the step width changes by more than 3.5 cm as the starting point of the step width freezing event; according to the starting point of the step width freezing event, compare the change in step width within 3 seconds before and after the marked point. If the step width changes by more than 2 cm, it is considered a step width precursor feature;

[0038] On the gait feature curve, mark the time point when the change in joint flexion and extension dispersion exceeds 10% as the starting point of the flexion and extension freezing event; according to the starting point of the flexion and extension freezing event, compare the change in joint flexion and extension dispersion within 3 seconds before and after the marked point. If the change exceeds 5%, it is considered a joint flexion and extension precursor feature;

[0039] Combine the speed precursor feature, symmetry precursor feature, step width precursor feature, and joint flexion and extension precursor feature to obtain the precursor attribute of the freezing event.

[0040] By marking the time point when the gait speed drops below 0.5 m / s on the gait feature curve, the present invention can accurately locate the starting moment of the speed freezing event, calculate the change rate of the gait speed within 3 seconds before and after the marked point. When the change rate is less than -0.2 m / s², it is determined as the speed precursor feature, which can quantify the severity of the gait speed change; by marking the time point when the gait symmetry index drops below 0.8 on the gait feature curve, the starting moment of the symmetry freezing event can be accurately located, providing a clear time reference for subsequent analysis; by comparing the change in gait symmetry within 5 seconds before and after the marked point, when the symmetry change exceeds 0.2 and the time interval is less than 1 second, it is determined as the symmetry precursor feature, which can quantify the severity and time characteristics of the gait symmetry change, providing an objective basis for the early identification of the freezing event; by marking the time point when the step length shortens to less than 68 cm on the gait feature curve, the starting moment of the step length freezing event can be accurately located; by comparing the change in step length within 3 seconds before and after the marked point, when the step length shortens by more than 5 cm, it is determined as the step length precursor feature, which can quantify the severity of the step length change, providing an objective basis for the early identification of the freezing event; by marking the time point when the step width change exceeds 3.5 cm on the gait feature curve, the starting moment of the step width freezing event can be accurately located; by comparing the change in step width within 3 seconds before and after the marked point, when the step width change exceeds 2 cm, it is determined as the step width precursor feature, which can quantify the severity of the step width change; by marking the time point when the joint flexion and extension dispersion change exceeds 10% on the gait feature curve, the starting moment of the flexion and extension freezing event can be accurately located; by comparing the change in joint flexion and extension dispersion within 3 seconds before and after the marked point, when the change exceeds 5%, it is determined as the joint flexion and extension precursor feature, which can quantify the severity of the joint flexion and extension change; by combining the speed precursor feature, symmetry precursor feature, step length precursor feature, step width precursor feature, and joint flexion and extension precursor feature, the precursor attribute of the freezing event is obtained, which can comprehensively reflect the multi-dimensional feature changes before the occurrence of the gait freezing event.

[0041] Preferably, step S3 includes the following steps:

[0042] Step S31: Extract the gait interruption precursor feature from the precursor attribute of the freezing event to obtain the gait interruption precursor feature; determine the interruption type for the gait interruption precursor feature to generate the gait interruption type;

[0043] Step S32: Compare the similarity between the types of the gait interruption types to obtain the inter-type similarity data; divide the precursor attribute of the freezing event into gait gradual change types according to the inter-type similarity data;

[0044] Step S33: Segment the time period of the freezing occurrence according to the freezing event characteristics. Taking the occurrence point of the freezing event characteristics as the center, extend 5 seconds forward and backward respectively, and divide it into the pre-freezing interval and the post-freezing interval;

[0045] Step S34: Mark the normal interval of the gait type according to the interval before freezing; mark the frozen interval of the gait type according to the interval after freezing;

[0046] Step S35: Measure the gait freezing cycle by comparing the normal interval of the gait type with the frozen interval of the gait type to generate a gait freezing cycle;

[0047] Step S36: Quantify the freezing cumulative frequency of the gait freezing cycle based on the freezing duration to obtain a gait freezing index.

[0048] The present invention extracts features of the precursor attributes of the freezing event, which can accurately identify the early signals of gait interruption; classifies the precursor features of gait interruption to generate gait interruption types, providing a clear classification basis for subsequent analysis; by comparing the similarities of gait interruption types, the correlation between different interruption types can be quantified. Classify the precursor attributes of the freezing event based on the similarity data between types into gait gradual change types, providing a classification basis for subsequent cycle measurement; with the occurrence point of the freezing event characteristics as the center, extend 5 seconds forward and backward respectively, divided into the interval before freezing and the interval after freezing, which can accurately locate the time range of the freezing event; mark the gait gradual change type based on the interval before freezing, which can clarify the characteristic interval of normal gait, and mark the gait gradual change type based on the interval after freezing, which can clarify the characteristic interval of frozen gait; by comparing the normal interval and the frozen interval of the gait type, measure the gait freezing cycle, which can quantify the periodic characteristics of the freezing event; quantify the gait freezing cycle based on the freezing duration, which can comprehensively reflect the severity of the freezing event.

[0049] Preferably, step S36 includes the following steps:

[0050] Step S361: Perform periodic segmentation processing on the freezing duration to obtain the segmented duration of the freezing type;

[0051] Step S362: Perform duration normalization processing on the segmented duration of the freezing type to obtain duration normalization data;

[0052] Step S363: Statistically analyze the freezing frequency of the gait freezing cycle according to the duration normalization data and determine the occurrence frequency of each freezing cycle to obtain freezing frequency distribution data;

[0053] Step S364: Perform cumulative calculation on the freezing frequency distribution data and accumulate the frequencies of each freezing cycle in chronological order to form a freezing cumulative frequency curve;

[0054] Step S365: Perform freezing frequency parameter mapping on the freezing cumulative frequency curve and divide the freezing frequency parameters into multiple quantization intervals, each interval corresponding to a quantization value, to generate freezing frequency quantization parameters;

[0055] Step S366: Perform weighted calculation on the freezing frequency quantization parameter to obtain the final gait freezing index.

[0056] The present invention performs periodic segmentation on the freezing duration, which can subdivide the freezing events according to periodic characteristics and provide basic data for subsequent duration normalization processing; performing normalization processing on the freezing type segmentation duration can eliminate the influence of different cycle lengths on the analysis and make the data comparable; based on the duration-normalized data, performing freezing frequency statistics on the gait freezing cycle to determine the occurrence frequency of each freezing cycle can quantify the periodic occurrence law of the freezing events; performing cumulative calculation on the freezing frequency distribution data and accumulating the frequencies of each freezing cycle in chronological order to form a freezing cumulative frequency curve can intuitively display the cumulative change trend of the freezing events over time; performing parameter mapping on the freezing cumulative frequency curve, dividing the freezing frequency parameter into multiple quantization intervals, and each interval corresponding to a quantization value can convert the continuous frequency data into quantifiable discrete parameters; performing weighted calculation on the freezing frequency quantization parameter can comprehensively reflect the severity of the gait freezing events and provide a quantitative basis for gait impairment assessment.

[0057] Preferably, step S4 includes the following steps:

[0058] Step S41: Arrange the freezing cycle data in chronological order, use the start time of the freezing cycle as the abscissa, and the freezing duration as the ordinate to plot the freezing cycle curve;

[0059] Step S42: Calculate the slope of the freezing cycle curve according to the gait freezing index. When the slope is greater than 0, it is determined as an increasing trend of gait freezing; when the slope is less than 0, it is determined as a decreasing trend of gait freezing;

[0060] Step S43: Combine the increasing trend of gait freezing and the decreasing trend of gait freezing to generate gait trend feature data;

[0061] Step S44: Divide the gait change trend into three intervals of mild, moderate, and severe impairment of gait impairment, and mark them with different colors respectively to obtain the gait change impairment color;

[0062] Step S45: Map the gait change impairment color to the degree of Parkinson's gait impairment and visualize the degree of gait impairment to generate a gait impairment assessment report.

[0063] By arranging the freeze cycle data in chronological order and plotting a curve, the present invention can visually display the changing trends of the start time and duration of the freeze cycle, providing a visual basis for subsequent trend analysis; calculating the slope of the freeze cycle curve based on the gait freezing index can quantify the changing trend of gait freezing. When the slope is greater than 0, it is determined that there is an enhanced trend of gait freezing, and when the slope is less than 0, it is determined that there is a weakened trend of gait freezing, providing a clear basis for subsequent trend analysis; combining the enhanced trend and weakened trend of gait freezing to generate gait change trend data can comprehensively reflect the overall change of gait freezing; dividing the gait change trend into three intervals of mild, moderate, and severe impairment and marking them with different colors respectively can visually distinguish the gait changes of different impairment degrees, providing a clear visual identifier for visual analysis. By mapping the gait change impairment color to the impairment degree of Parkinson's disease gait and performing visual processing, an intuitive gait impairment assessment report can be generated, providing clear and accurate visual basis for relevant analysis.

[0064] The present invention also provides a method for establishing a Parkinson's disease gait impairment assessment model for the above-mentioned method for establishing a Parkinson's disease gait impairment assessment. The Parkinson's disease gait impairment assessment model includes:

[0065] An image monitoring module for continuously monitoring the gait images of Parkinson's disease patients; when a gait continuity interruption of the gait image is detected, it is determined as a gait freezing event, and the freezing event characteristics, freezing occurrence time period, and freezing duration of the gait freezing event are recorded;

[0066] A gait feature curve construction module for determining gait feature parameters based on the gait images; extracting the gait spatio-temporal feature parameters of the gait feature parameters and constructing a gait feature curve according to the gait spatio-temporal feature parameters; identifying the precursor attributes of the freezing event characteristics based on the gait feature curve to obtain the freezing event precursor attributes;

[0067] A gait freezing quantification module for classifying the freezing event precursor attributes into gait gradual change types; detecting the gait freezing cycle for the gait gradual change types according to the freezing occurrence time period to generate a gait freezing cycle; quantifying the freezing cumulative frequency of the gait freezing cycle based on the freezing duration to obtain a gait freezing index;

[0068] An impairment degree assessment module for determining the gait change trend based on the freeze cycle data and the gait freezing index, and assessing the impairment degree of Parkinson's disease gait for the gait change trend to generate a gait impairment assessment report.

[0069] The image monitoring module of the present invention monitors the gait of Parkinson's disease patients in real time through a high-resolution image acquisition device, ensuring that a complete sequence of gait images can be captured at any time point, and being able to continuously record the walking process of the patients, providing a comprehensive data basis for subsequent analysis; analyzing the gait images based on image processing algorithms, and automatically determining a gait freezing event when a gait continuity interruption is detected. At the same time, recording the characteristics of the freezing event, including the time period when the freezing occurs, the duration of the freezing, and the morphological characteristics of the freezing event, ensuring the accuracy and integrity of the data and avoiding errors caused by manual intervention. Through the gait feature curve construction module, spatio-temporal gait feature parameters are extracted from the gait images, including key parameters such as step length, step width, walking speed, and gait cycle. These parameters are calculated through image analysis algorithms, ensuring the objectivity and repeatability of the data. Based on the extracted spatio-temporal gait feature parameters, a gait feature curve is constructed, with time as the horizontal axis and gait feature parameters as the vertical axis, which can intuitively reflect the change trend of gait parameters over time. And through this curve processing, the system can capture the dynamic process of gait changes; by analyzing the gait feature curve, identifying the characteristic changes before the occurrence of the freezing event, that is, the precursor attributes of the freezing event, this identification process is based on the morphological analysis of the curve and the change trend of parameters, and can accurately locate the precursor characteristics of the freezing event. Through the gait freezing quantification module, the precursor attributes of the freezing event are divided into different gait gradual change types, this division is based on the morphological characteristics and parameter change rules of the gait feature curve, and can classify complex gait changes; and according to the time period when the freezing occurs, periodic detection of the gait gradual change types is carried out. By analyzing the periodic changes of the gait feature curve, the periodic pattern of gait freezing can be accurately identified, thereby revealing the regularity of the gait freezing event; based on the duration of the freezing, quantitative analysis of the gait freezing cycle is carried out, and it is obtained by calculating the weighted sum of the cumulative frequency and the duration of the freezing event, which can comprehensively reflect the severity of gait freezing and provide a unified quantitative standard for the evaluation of the degree of gait impairment. Through the degree of impairment evaluation module, based on the freezing cycle data and the gait freezing index, analyzing the trend of gait changes through a mathematical model, being able to comprehensively consider the regularity of the freezing cycle and the change trend of the freezing index, and thus accurately judge the overall situation of gait impairment; according to the trend of gait changes, quantitatively evaluating the degree of gait impairment, this evaluation process is based on a preset quantitative standard, and by calculating the difference between the gait freezing index and normal gait parameters, an objective and quantitative evaluation result can be provided; generating a detailed gait impairment evaluation report according to the evaluation result, this report includes detailed records of the freezing event, gait feature curves, freezing cycle analysis results, and quantitative evaluation of the degree of gait impairment. The report is presented in the form of charts and data, and can intuitively display the detailed situation of gait changes, providing comprehensive data support for relevant research.Therefore, through data processing technology and image processing technology, the present invention realizes gait monitoring of Parkinson's disease patients and identifies the characteristics of gait freezing, so as to improve the accuracy of gait impairment assessment for Parkinson's disease and shorten the time used in the impairment assessment process.

[0070] A computer-readable storage medium stores a computer program, wherein the computer program is used to execute the established method for assessing gait impairment in Parkinson's disease. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 It is a schematic flowchart of the steps of an established method for assessing gait impairment in Parkinson's disease;

[0072] Figure 2 For Figure 1 It is a schematic flowchart of the detailed implementation steps of step S1 in

[0073] Figure 3 For Figure 1 It is a schematic flowchart of the detailed implementation steps of step S4 in

[0074] The realization, functional characteristics and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0075] The technical method of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0076] In addition, the accompanying drawings are only schematic diagrams of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and thus their repeated description will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0077] It should be understood that although terms such as "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed related items.

[0078] To achieve the above object, please refer to Figures 1 to 3 , a method for establishing an assessment method for impaired gait in Parkinson's disease, the method comprising the following steps:

[0079] Step S1: Continuously monitor the gait images of Parkinson's disease patients; when a gait continuity interruption of the gait image is detected, it is determined as a gait freezing event, and the freezing event characteristics, the freezing occurrence time period, and the freezing duration of the gait freezing event are recorded;

[0080] Step S2: Determine gait feature parameters based on the gait images; extract the spatio-temporal gait feature parameters of the gait feature parameters, and construct a gait feature curve according to the spatio-temporal gait feature parameters; identify the precursor attributes of the freezing event characteristics according to the gait feature curve to obtain the freezing event precursor attributes;

[0081] Step S3: Divide the freezing event precursor attributes into gait gradual change types; perform gait freezing cycle detection on the gait gradual change types according to the freezing occurrence time period to generate a gait freezing cycle; perform freezing cumulative frequency quantization on the gait freezing cycle based on the freezing duration to obtain a gait freezing index;

[0082] Step S4: Determine the gait change trend based on the freezing cycle data and the gait freezing index, and evaluate the degree of impaired gait in Parkinson's disease for the gait change trend to generate a gait impairment assessment report.

[0083] The present invention monitors the gait of Parkinson's disease patients in real time through a high-resolution image acquisition device, ensuring that a complete sequence of gait images can be captured at any point in time, continuously recording the walking process of the patients, and providing a comprehensive data basis for subsequent analysis; analyzes the gait images based on image processing algorithms, and automatically determines a gait freezing event when a gait continuity interruption is detected. At the same time, the characteristics of the freezing event are recorded, including the time period when the freezing occurs, the duration of the freezing, and the morphological characteristics of the freezing event, ensuring the accuracy and integrity of the data and avoiding errors caused by manual intervention. Gait spatio-temporal characteristic parameters are extracted from the gait images, including key parameters such as step length, step width, walking speed, and gait cycle. These parameters are calculated through image analysis algorithms, ensuring the objectivity and repeatability of the data. Based on the extracted gait spatio-temporal characteristic parameters, a gait characteristic curve is constructed, with time as the horizontal axis and gait characteristic parameters as the vertical axis, which can intuitively reflect the changing trend of gait parameters over time. And through this curve processing, the system can capture the dynamic process of gait changes; by analyzing the gait characteristic curve, the characteristic changes before the occurrence of the freezing event are identified, that is, the precursor attributes of the freezing event. This identification process is based on the morphological analysis of the curve and the changing trend of parameters, and can accurately locate the precursor characteristics of the freezing event. The precursor attributes of the freezing event are divided into different gait gradual change types. This division is based on the morphological characteristics and parameter change rules of the gait characteristic curve, and can classify complex gait changes; and according to the time period when the freezing occurs, periodic detection of the gait gradual change types is carried out. By analyzing the periodic changes of the gait characteristic curve, the periodic pattern of gait freezing can be accurately identified, thereby revealing the regularity of gait freezing events; a quantitative analysis of the gait freezing cycle is carried out based on the freezing duration and is obtained by calculating the weighted sum of the cumulative frequency and the duration of the freezing event, which can comprehensively reflect the severity of gait freezing and provide a unified quantitative standard for the evaluation of gait impairment degree. Based on the freezing cycle data and the gait freezing index, the trend of gait changes is analyzed through a mathematical model, which can comprehensively consider the regularity of the freezing cycle and the changing trend of the freezing index, so as to accurately judge the overall situation of gait impairment; according to the trend of gait changes, a quantitative evaluation of the gait impairment degree is carried out. This evaluation process is based on a preset quantitative standard. By calculating the difference between the gait freezing index and normal gait parameters, an objective and quantitative evaluation result can be provided; a detailed gait impairment evaluation report is generated according to the evaluation result. The report includes a detailed record of the freezing event, the gait characteristic curve, the analysis result of the freezing cycle, and the quantitative evaluation of the gait impairment degree. The report is presented in the form of charts and data, which can intuitively display the detailed situation of gait changes and provide comprehensive data support for relevant research. Therefore, the present invention realizes the gait monitoring of Parkinson's disease patients through data processing technology and image processing technology, and identifies the gait freezing characteristics, so as to improve the accuracy of Parkinson's disease gait impairment evaluation and shorten the time used in the impairment evaluation process.

[0084] In an embodiment of the present invention, with reference to Figure 1 As shown, it is a schematic diagram of the step flow of a method for establishing an assessment method for gait impairment in Parkinson's disease according to the present invention. In this example, the method for establishing an assessment method for gait impairment in Parkinson's disease includes the following steps:

[0085] Step S1: Continuously monitor the gait images of Parkinson's disease patients; when a gait continuity interruption in the gait image is detected, it is determined as a gait freezing event, and the freezing event characteristics, the freezing occurrence time period, and the freezing duration of the gait freezing event are recorded;

[0086] In an embodiment of the present invention, micro inertial measurement unit (IMU) sensors are respectively installed on the feet, knees, and waist of Parkinson's disease patients to collect acceleration, angular velocity, and attitude information in real time. At the same time, multiple high-resolution cameras are installed above the walking area of the patients to form a stereo vision monitoring system for capturing the gait images of the patients. The frame rate of the cameras is 60fps, and the resolution is 1920×1080 pixels to ensure that every detail of the gait can be clearly recorded; preprocess the collected gait images, including grayscale conversion, denoising, and edge detection. First, convert the color image into a grayscale image to reduce the data volume and improve the processing efficiency. Then, use Gaussian filtering to denoise the grayscale image and remove the random noise in the image. Finally, adopt the Canny edge detection algorithm to extract the edge information in the image for subsequent gait feature extraction; based on the preprocessed image data, extract gait features. First, identify the body contour and leg movement trajectory of the patient through the background subtraction method. Then, calculate the key parameters of the gait, including step length, step width, walking speed, gait symmetry, swing time, and support time, etc. At the same time, combine the IMU sensor data to calculate the acceleration, angular velocity, and attitude angle change of the patient to comprehensively reflect the dynamic characteristics of the gait; use a deep learning algorithm to analyze the gait features and detect gait continuity interruptions. The specific method is to construct a gait freezing detection model based on a convolutional neural network (CNN). The input of this model is gait images and sensor data, and the output is the determination result of the gait freezing event. The model learns the feature differences between normal and frozen gait states through the training data set. When the detected gait features are similar to the frozen state, it is determined as a gait freezing event; when a gait freezing event is detected, the system automatically records the relevant features of the freezing event. The freezing event characteristics include changes in gait parameters (such as shortened step length, reduced walking speed, extended double support time, etc.), the time stamp of the freezing occurrence (accurate to the millisecond level), and the freezing duration (obtained by calculating the difference between the start and end time stamps of the freezing). These feature data are stored in the local database for subsequent analysis and research use.

[0087] Step S2: Determine gait feature parameters based on the gait image; extract the spatio-temporal feature parameters of the gait feature parameters, and construct a gait feature curve according to the spatio-temporal feature parameters of the gait; identify the precursor attributes of the freezing event features according to the gait feature curve to obtain the freezing event precursor attributes.

[0088] In the embodiment of the present invention, first, the OpenPose human pose recognition technology is used to analyze the gait image and extract the two-dimensional coordinate information of the human key points. OpenPose detects each key point of the human body in the image through a deep learning model, including the ankles, knees, hips, etc., and outputs the precise positions of these key points. These key point data will serve as the basis for the subsequent extraction of gait feature parameters. Next, based on the extracted key point coordinates, the gait feature parameters are calculated. Specifically, the step length is obtained by calculating the distance between the center points of the two ankles; the step width is calculated by measuring the horizontal distance between the center points of the two ankles; the walking speed is determined by the product of the step length and the step frequency; the single support time refers to the time when a single foot touches the ground and is calculated by analyzing the movement trajectory of the ankle key points; the double support time refers to the time when both feet touch the ground simultaneously and is also obtained by analyzing the movement trajectory of the ankle key points. These parameters can comprehensively reflect the gait characteristics of the patient. Subsequently, the spatio-temporal feature parameters of the gait are extracted, and a gait feature curve is constructed. Taking parameters such as the step length, step frequency, and single support time as examples, the changes of these parameters over time are plotted as curves. In order to smooth the curve and remove noise, the Savitzky-Golay filter is used for processing. This filter smooths the data through polynomial fitting while retaining the basic shape of the signal. In practical applications, the window size of the filter is set to 21, and the polynomial order is 2. This parameter configuration can better retain the detailed features of the signal while removing noise. Finally, analyze the change trend of the gait feature curve before the occurrence of the freezing event and identify the precursor attributes of the freezing event. The specific parameters analyzed include the step length change rate (the step length shortens by more than 10%), the step frequency change rate (the step frequency drops by more than 20%), and the double support time change rate (the double support time increases by more than 30%).

[0089] Step S3: Classify the freezing event precursor attributes into gait gradual change types; perform gait freezing cycle detection on the gait gradual change types according to the freezing occurrence time period to generate a gait freezing cycle; perform freezing cumulative frequency quantization on the gait freezing cycle based on the freezing duration to obtain a gait freezing index.

[0090] In the embodiments of the present invention, first, the precursor attributes of the freezing event are classified to divide the types of gait gradual changes. By analyzing the changes in step length and step frequency in the gait feature curve, the types of gait gradual changes are divided into "slow type" and "fast type". The specific operation is as follows: Calculate the step length shortening rate and the step frequency decrease rate. The step length shortening rate is obtained by comparing the step length changes before and after freezing, and the step frequency decrease rate is obtained by comparing the step frequency changes before and after freezing. When the step length shortening rate is less than 10% and the step frequency decrease rate is less than 20%, it is determined as a "slow type" gait gradual change; when the step length shortening rate is greater than or equal to 10% and the step frequency decrease rate is greater than or equal to 20%, it is determined as a "fast type" gait gradual change. Subsequently, according to the time period when freezing occurs, the gait freezing cycle detection is performed on the types of gait gradual changes. Using the time series analysis technology and combining with the periodic changes of the gait feature curve, the starting point and the ending point of the gait freezing cycle are determined. The specific operation is as follows: In the gait feature curve, the starting point and the ending point of the freezing cycle are identified by detecting the significant change points of the step length and the step frequency. The starting point is defined as the moment when the step length shortening rate exceeds 10% and the step frequency decrease rate exceeds 20%; the ending point is defined as the moment when the step length recovers to 80% of that before shortening and the step frequency recovers to 80% of that before decreasing. In this way, the gait freezing cycle is extracted from the gait feature curve, and the duration of each freezing cycle is recorded. Finally, based on the freezing duration, the gait freezing cycle is quantified by the freezing cumulative frequency to obtain the gait freezing index. The specific operation is as follows: Count the freezing duration within each gait freezing cycle and calculate its proportion in the total gait cycle. The proportion values of all gait freezing cycles are accumulated to obtain the gait freezing index. This index reflects the cumulative frequency and severity of gait freezing in patients within a certain period of time, and can be used to quantitatively evaluate the gait impairment of Parkinson's disease patients.

[0091] Step S4: Determine the gait change trend based on the freezing cycle data and the gait freezing index, and evaluate the degree of gait impairment in Parkinson's disease for the gait change trend, and generate a gait impairment evaluation report.

[0092] In the embodiments of the present invention, the freezing cycle data is analyzed to extract the key features of the gait change trend. The Gait Freezing Index (FI) is used as a quantitative index to determine the gait change trend by comparing the changes in gait parameters before and after the freezing event occurs. The specific operations include: calculating the average value and coefficient of variation of parameters such as step length, walking speed, and step frequency within the freezing cycle, and analyzing the change amplitude of these parameters before and after the freezing event occurs. For example, indicators such as step length shortening rate, walking speed decline rate, and double support time increase rate can be used to reflect the trend of gait changes. Secondly, the degree of gait impairment in Parkinson's disease is evaluated according to the gait change trend. The Multi-output Random Forest (MRFR) algorithm is used to classify and quantify the degree of gait impairment. This algorithm classifies patients into three categories: mild, moderate, and severe impairment by analyzing the change patterns of gait parameters. The specific operation is: inputting key features such as the gait freezing index, step length shortening rate, and walking speed decline rate, and evaluating the degree of gait impairment of patients through the classification model obtained by algorithm training. Finally, a gait impairment assessment report is generated. The assessment report includes the patient's basic information, gait freezing index, gait change trend analysis results, and classification results of the degree of gait impairment. The report details the changes in gait parameters, such as step length shortening rate, walking speed decline rate, etc.

[0093] As an example of the present invention, refer to Figure 2 As shown, in this example, step S1 includes:

[0094] Step S11: Set the frame rate of the binocular camera to 40 - 60 frames per second, the resolution to 1920×1080 pixels, and the angle between the binocular camera and the patient's walking path to 45°;

[0095] Step S12: Collect the complete cycle of each patient's walk, including the starting gait, intermediate gait, and ending gait, and the duration of each collection is 3 minutes;

[0096] Step S13: Activate the automatic tracking function of the binocular camera to continuously monitor the walking path, number of steps, walking speed, and walking actions of Parkinson's disease patients to obtain gait images;

[0097] Step S14: Record the number of swings of the patient's gait pace in the gait image, mark the situation of zero swings in two consecutive cycles of the patient's gait pace; determine the gait interruption point for the situation of zero swings in two consecutive cycles to obtain gait continuity interruption data;

[0098] Step S15: Perform a gait freezing judgment on the gait image based on the gait continuity interruption data to obtain a gait freezing event, and record the freezing event characteristics, the freezing occurrence time period, and the freezing duration of the gait freezing event.

[0099] In the embodiment of the present invention, first, according to the requirements of step S11, set the frame rate of the binocular camera to 50 frames per second, the resolution to 1920×1080 pixels, and set the angle between the binocular camera and the patient's walking path to 45°. This setting can ensure that clear and comprehensive-view gait images are obtained during the acquisition process, providing a high-quality data basis for subsequent analysis. Then, in step S12, collect the complete cycle of each patient's walk, including the starting gait, the intermediate gait, and the ending gait, and the duration of each collection is 3 minutes. In this way, the gait characteristics of the patient at different walking stages can be comprehensively recorded to ensure the integrity and representativeness of the data. In step S13, activate the automatic tracking function of the binocular camera to continuously monitor the walking path, the number of walking steps, the walking speed, and the walking actions of the Parkinson's disease patient to obtain gait images. The automatic tracking function can capture the patient's movement trajectory in real time to ensure that key information is not lost during the acquisition process. In specific operations, use the depth information and visual tracking algorithm of the binocular camera to track the patient's limb movements in real time and record their gait characteristics. Subsequently, in step S14, record the number of swings of the patient's gait steps in the gait image, and mark the situation where the number of swings of the patient's gait steps is zero in two consecutive cycles. By analyzing the limb movement data in the gait image, identify the situation where the number of swings is zero in two consecutive cycles and mark it as a potential gait interruption point. These interruption points are important bases for judging gait continuity interruption. In specific operations, use gait analysis software to process the gait image, extract the number of swings of each step, and determine the situation of zero number of swings in two consecutive cycles through time series analysis. Finally, in step S15, perform a gait freezing judgment on the gait image based on the gait continuity interruption data to obtain a gait freezing event, and record the freezing event characteristics, the freezing occurrence time period, and the freezing duration of the gait freezing event. By analyzing the changes in the time-space gait parameters before and after the interruption point, determine the specific characteristics of the gait freezing event, including the time point when the freezing occurs, the duration of the freezing, and the changes in the gait parameters during the freezing period. These data provide key information for subsequent gait impairment assessment. In specific operations, use a gait analysis system to analyze the time series data before and after the interruption point and calculate the change rate of the gait parameters to determine the characteristics of the gait freezing event.

[0100] The gait feature parameters determined based on the gait image include:

[0101] Divide the gait image into multiple consecutive frame sequences, where each frame sequence corresponds to a gait cycle;

[0102] In each frame sequence, the foot joints, knee joints, and ankle joints are extracted to obtain human joint point information; the displacement time change of the human joint point information in adjacent frames is calculated to generate a gait motion cycle;

[0103] The distance between the foot joint and the contact point in two consecutive gait motion cycles is calculated to obtain step length data; the lateral distance between the left and right foot joints and the contact point is measured to obtain step width data;

[0104] The step length data and the gait motion cycle are used for gait speed measurement; based on the gait speed and step width data, the gait symmetry of the gait motion cycle is determined;

[0105] The flexion and extension phase angles of the knee joint and ankle joint in two consecutive gait motion cycles are calculated, and the flexion and extension phase angles are mapped to flexion and extension dispersion to obtain joint flexion and extension dispersion;

[0106] The gait motion cycle, step length data, step width data, gait speed, gait symmetry, and joint flexion and extension dispersion are combined into gait feature parameters.

[0107] In the embodiments of the present invention, the gait image is divided into multiple consecutive frame sequences, and each frame sequence corresponds to a gait cycle. Using computer vision technology, combined with the OpenPose framework, human pose recognition is performed on the gait image to extract the position information of the foot joints, knee joints, and ankle joints. By detecting the key points in each frame of the image, the two-dimensional coordinate data of the human joint points are obtained. Then, the displacement time change of the human joint point information in adjacent frames is calculated to generate a gait motion cycle. The specific method is to calculate the displacement of the key points in each frame and convert the displacement into time series data in combination with the frame rate (such as 50 frames per second), thereby generating a gait motion cycle. Subsequently, the distance between the foot joint and the contact point in two consecutive gait motion cycles is calculated to obtain step length data. At the same time, the lateral distance between the left and right foot joints and the contact point is measured to obtain step width data. The step length is obtained by calculating the distance between the center points of the two heels, and the step width is calculated by measuring the lateral distance between the center points of the two ankles. The step length data and the gait motion cycle are used for gait speed measurement, and the specific formula is the step length divided by the time of the gait motion cycle. Based on the gait speed and step width data, the gait symmetry of the gait motion cycle is determined by calculating the differences in the step lengths and step widths of the left and right feet to evaluate the gait symmetry. Further, the flexion and extension phase angles of the knee joint and ankle joint in two consecutive gait motion cycles are calculated, and the flexion and extension phase angles are mapped to flexion and extension dispersion to obtain joint flexion and extension dispersion. By analyzing the change range and fluctuation degree of the joint angles, the flexion and extension dispersion of the joints is quantified. Finally, the gait motion cycle, step length data, step width data, gait speed, gait symmetry, and joint flexion and extension dispersion are combined into gait feature parameters, and these parameters are integrated by a gait analysis system and used for subsequent gait impairment assessment.

[0108] The spatio-temporal gait feature parameters for extracting gait feature parameters, and constructing a gait feature curve based on the spatio-temporal gait feature parameters includes:

[0109] Extract the cycle time information of the gait feature parameters, and divide the cycle time information into a time period sequence; parameterize the time period sequence to obtain the time period sequence parameters;

[0110] Based on the time period sequence parameters, perform gait spatial feature recognition on the gait feature parameters, and quantify the feature parameters of the gait spatial features to obtain the time period sequence parameters;

[0111] Arrange the time period sequence parameters in chronological order to form time-ordered data;

[0112] Use the time-ordered data as the horizontal axis and the time period sequence parameters as the vertical axis to construct an initial gait feature curve;

[0113] Perform curve smoothness processing on the initial gait feature curve to generate a gait feature curve.

[0114] In the embodiments of the present invention, computer vision technology is used to process gait images, extract the periodic time information of gait feature parameters, and divide it into a time period sequence; specifically, the OpenPose framework is used to perform human pose recognition on gait images to extract the position information of the ankle joint, knee joint, and ankle joint. Based on this key point information, calculate the change of gait feature parameters over time to generate time series data of the gait motion cycle; then, parameterize the time period sequence to obtain time period sequence parameters. The specific method is to calculate parameters such as step length, step width, and gait speed within each time period, and use these parameters as the eigenvalue of the time period sequence. For example, the step length is obtained by calculating the distance between the center points of the two ankles, and the step width is calculated by measuring the horizontal distance between the center points of the two ankles. Subsequently, based on the time period sequence parameters, gait space feature recognition is performed on the gait feature parameters, and the gait space features are quantified in terms of feature parameters. By analyzing the changes of gait feature parameters in different time periods, indicators such as gait symmetry and joint flexion and extension dispersion are calculated. For example, gait symmetry can be evaluated by calculating the difference in step length and step width between the left and right feet, and the joint flexion and extension dispersion is quantified by analyzing the change range and fluctuation degree of the flexion and extension phase angles of the knee joint and ankle joint. After that, the time period sequence parameters are arranged in chronological order to form time-ordered data. These data reflect the change trend of gait feature parameters over time and provide a basis for constructing subsequent gait feature curves. Finally, using the time-ordered data as the horizontal axis and the time period sequence parameters as the vertical axis, an initial gait feature curve is constructed. The initial gait feature curve is processed for curve smoothness, and the Savitzky-Golay filter is used to smooth the curve. This filter fits the data through local polynomial regression and can retain the key features of the signal while smoothing the noise. The specific parameter settings are a window size of 21 and a polynomial order of 2.

[0115] The precursor attributes for identifying the freezing event features according to the gait feature curve include:

[0116] On the gait feature curve, mark the time point when the gait speed drops below 0.5 m / s as the starting point of the speed freezing event; calculate the change rate of the gait speed within 3 seconds before and after the marked point based on the starting point of the speed freezing event. If the change rate is less than -0.2 m / s², it is determined as the speed precursor feature;

[0117] On the gait feature curve, mark the time point when the gait symmetry index drops below 0.8 as the starting point of the symmetry freezing event; compare the change in gait symmetry within 5 seconds before and after the marked point based on the starting point of the symmetry freezing event. If the symmetry change exceeds 0.2, record the time interval of the gait symmetry change. If the interval is less than 1 second, it is determined as the symmetry precursor feature;

[0118] On the gait feature curve, mark the time point when the step length shortens to less than 68 cm as the starting point of the step length freezing event; according to the starting point of the step length freezing event, compare the change in step length within 3 seconds before and after the marked point. If the step length shortens by more than 5 cm, it is determined as the step length precursor feature;

[0119] On the gait feature curve, mark the time point when the step width changes by more than 3.5 cm as the starting point of the step width freezing event; according to the starting point of the step width freezing event, compare the change in step width within 3 seconds before and after the marked point. If the step width changes by more than 2 cm, it is determined as the step width precursor feature;

[0120] On the gait feature curve, mark the time point when the change in joint flexion and extension dispersion exceeds 10% as the starting point of the flexion and extension freezing event; according to the starting point of the flexion and extension freezing event, compare the change in joint flexion and extension dispersion within 3 seconds before and after the marked point. If the change exceeds 5%, it is determined as the joint flexion and extension precursor feature;

[0121] Combine the speed precursor feature, symmetry precursor feature, step width precursor feature, and joint flexion and extension precursor feature to obtain the precursor attribute of the freezing event.

[0122] In the embodiments of the present invention, key indicators are extracted from the gait feature curve. The OpenPose framework is used to perform human pose recognition on gait video data, and the position information of key points such as the ankles, knees, and ankles is extracted. Based on this key point information, gait feature parameters are calculated, including gait speed, gait symmetry, step length, step width, and joint flexion and extension dispersion. On the gait feature curve, when the gait speed drops below 0.5 m / s, mark this time point as the starting point of the speed freeze event. For this marked point, calculate the change rate of the gait speed within 3 seconds before and after it. The specific operation is to calculate the change amount of the speed divided by the time interval through the difference method. If the change rate is less than -0.2 m / s², it is determined as a speed precursor feature. On the gait feature curve, when the gait symmetry index drops below 0.8, mark this time point as the starting point of the symmetry freeze event. Based on this starting point, compare the change in gait symmetry within 5 seconds before and after the marked point. If the symmetry change exceeds 0.2, record the time interval of the gait symmetry change. If the interval is less than 1 second, it is determined as a symmetry precursor feature. On the gait feature curve, when the step length shortens to less than 68 cm, mark this time point as the starting point of the step length freeze event. For this starting point, compare the change in step length within 3 seconds before and after the marked point. If the step length shortens by more than 5 cm, it is determined as a step length precursor feature. On the gait feature curve, when the step width changes by more than 3.5 cm, mark this time point as the starting point of the step width freeze event. For this starting point, compare the change in step width within 3 seconds before and after the marked point. If the step width change exceeds 2 cm, it is determined as a step width precursor feature. On the gait feature curve, when the joint flexion and extension dispersion changes by more than 10%, mark this time point as the starting point of the flexion and extension freeze event. For this starting point, compare the change in joint flexion and extension dispersion within 3 seconds before and after the marked point. If the change exceeds 5%, it is determined as a joint flexion and extension precursor feature.

[0123] Preferably, step S3 includes the following steps:

[0124] Step S31: Extract the gait interruption precursor features from the precursor attributes of the freeze event to obtain the gait interruption precursor features; determine the interruption type for the gait interruption precursor features to generate the gait interruption type;

[0125] Step S32: Compare the similarities between the gait interruption types to obtain the inter-type similarity data; divide the precursor attributes of the freeze event into gait gradual change types according to the inter-type similarity data;

[0126] Step S33: Segment the time of the freeze occurrence period according to the freeze event characteristics. Taking the occurrence point of the freeze event characteristics as the center, extend 5 seconds forward and backward respectively, and divide it into a pre-freeze interval and a post-freeze interval;

[0127] Step S34: Mark the normal interval of the gait type according to the interval before freezing; mark the frozen interval of the gait type according to the interval after freezing;

[0128] Step S35: Measure the gait freezing cycle by comparing the normal interval of the gait type with the frozen interval of the gait type to generate a gait freezing cycle;

[0129] Step S36: Quantify the freezing cumulative frequency of the gait freezing cycle based on the freezing duration to obtain a gait freezing index.

[0130] In the embodiments of the present invention, gait interruption precursor features are extracted from the gait feature curve. Using time series analysis technology, key indicators in the gait feature curve (such as gait speed, gait symmetry, step length, step width, and joint flexion and extension dispersion) are monitored. When the gait speed drops below 0.5 m / s, mark this time point as the starting point of the speed freeze event, and calculate the change rate of the speed within 3 seconds before and after it. If the change rate is less than -0.2 m / s², it is determined as the speed precursor feature. At the same time, when the gait symmetry index drops below 0.8, mark it as the starting point of the symmetry freeze event, and compare the change in symmetry within 5 seconds before and after the marked point. If the change exceeds 0.2 and the time interval is less than 1 second, it is determined as the symmetry precursor feature. In addition, when the step length shortens to less than 68 cm, mark it as the starting point of the step length freeze event; when the step width changes by more than 3.5 cm, mark it as the starting point of the step width freeze event. Compare the changes within 3 seconds before and after the marked point respectively. If the step length shortens by more than 5 cm or the step width changes by more than 2 cm, it is determined as the corresponding precursor feature. Finally, integrate the above precursor features to determine the gait interruption type. Based on the extracted gait interruption type, calculate the similarity between types. By calculating the Euclidean distance or cosine similarity between different types of precursor features, generate similarity data between types. According to the similarity data, divide the precursor attributes of the freeze event into different gait gradual change types, such as "slow type" and "fast type". According to the freeze event characteristics, with the occurrence point of the freeze event as the center, extend 5 seconds forward and backward respectively, and divide it into the pre-freeze interval and the post-freeze interval. This operation is achieved through time series analysis to ensure that the data intervals before and after freezing can completely cover the start and end of the freeze event. In the pre-freeze interval, mark the gait gradual change type to determine the normal gait type interval; in the post-freeze interval, mark the gait type freeze interval. This process is achieved by comparing the changes in gait feature parameters before and after freezing, such as gait speed, step length, and gait symmetry, etc.; compare and analyze the normal gait type interval and the gait type freeze interval, and generate the gait freeze cycle by calculating the change frequency of gait feature parameters in the two intervals. The specific operation includes calculating the change rate of gait speed, step length, and gait symmetry before and after freezing, and determining the freeze cycle based on this. Based on the freeze duration, conduct a quantitative analysis of the gait freeze cycle. By statistically calculating the duration of each gait freeze cycle and calculating its proportion in the total gait cycle, this index reflects the cumulative frequency and severity of the gait freeze event, providing a quantitative basis for the assessment of Parkinson's gait impairment.

[0131] Preferably, step S36 includes the following steps:

[0132] Step S361: Perform periodic segmentation processing on the freeze duration to obtain the freeze type segmentation duration;

[0133] Step S362: Perform duration normalization processing on the split duration of the freezing type to obtain duration normalization data;

[0134] Step S363: Statistically calculate the freezing frequency of the gait freezing cycle based on the duration normalization data, and determine the occurrence frequency of each freezing cycle to obtain freezing frequency distribution data;

[0135] Step S364: Perform cumulative calculation on the freezing frequency distribution data, and accumulate the frequencies of each freezing cycle in chronological order to form a freezing cumulative frequency curve;

[0136] Step S365: Perform freezing frequency parameter mapping on the freezing cumulative frequency curve, divide the freezing frequency parameters into multiple quantization intervals, each interval corresponds to a quantization value, and generate freezing frequency quantization parameters;

[0137] Step S366: Perform weighted calculation on the freezing frequency quantization parameters to obtain the final gait freezing index.

[0138] In the embodiments of the present invention, the duration of the freezing event is processed by periodic segmentation. Through the timing analysis technology, the duration of the freezing event is divided into multiple independent freezing cycles. The duration of each freezing cycle starts from the starting point of the freezing event and ends at the ending point of the freezing event. The purpose of the segmentation process is to decompose the continuous freezing event into multiple independent segments for subsequent analysis. The duration of the segmented freezing cycles is normalized. The purpose of the normalization process is to unify freezing cycles of different lengths into a standardized range for subsequent statistical analysis. The specific operation is to divide the duration of each freezing cycle by the sum of the durations of all freezing cycles to obtain the normalized duration data. Based on the normalized duration data, the frequency of the gait freezing cycles is statistically analyzed. By counting the occurrence frequency of each freezing cycle, freezing frequency distribution data is generated. The specific operation is to calculate the proportion of each freezing cycle in the total gait cycle and record it as the freezing frequency distribution data. The freezing frequency distribution data is cumulatively calculated, and the frequencies of each freezing cycle are cumulatively arranged in chronological order to form a freezing cumulative frequency curve. The cumulative frequency curve reflects the cumulative occurrence probability of the freezing event in the gait cycle and can intuitively display the severity of the freezing event. The freezing cumulative frequency curve is subjected to parameter mapping, and the freezing frequency parameters are divided into multiple quantization intervals. Each interval corresponds to a quantization value for quantitatively evaluating the severity of the freezing event. For example, the freezing frequency parameters can be divided into three quantization intervals: mild (0-20%), moderate (20%-50%), and severe (50%-100%). Finally, the weighted calculation of the freezing frequency quantization parameters is performed to obtain the final gait freezing index. The purpose of the weighted calculation is to comprehensively consider the severity of the freezing events in different quantization intervals and generate a quantization index that can comprehensively reflect the gait freezing situation. The specific operation is to perform weighted summation on the freezing frequency quantization parameters according to the weights of each quantization interval to finally obtain the gait freezing index.

[0139] As an example of the present invention, refer to Figure 3 shown, in this example, step S4 includes:

[0140] Step S41: Arrange the freezing cycle data in chronological order, take the starting time of the freezing cycle as the abscissa, and the freezing duration as the ordinate to plot the freezing cycle curve;

[0141] Step S42: Calculate the slope of the freezing cycle curve according to the gait freezing index. When the slope is greater than 0, it is determined that there is an increasing trend of gait freezing; when the slope is less than 0, it is determined that there is a decreasing trend of gait freezing;

[0142] Step S43: Combine the increasing trend of gait freezing and the decreasing trend of gait freezing to generate gait trend characteristic data;

[0143] Step S44: Divide the gait change trend into three intervals of mild, moderate, and severe gait impairment, and mark them with different colors respectively to obtain the gait change impairment color;

[0144] Step S45: Map the gait change impairment color to the degree of Parkinson's gait impairment and visualize the degree of gait impairment to generate a gait impairment assessment report.

[0145] In the embodiment of the present invention, the freezing cycle data is arranged in chronological order. Taking the start time of the freezing cycle as the abscissa and the freezing duration as the ordinate, a freezing cycle curve is plotted. Through time series analysis technology, the start time and duration of each freezing cycle are extracted and visualized on a two-dimensional plane. This process utilizes the gait freezing index and time series analysis method, which can intuitively display the time distribution of freezing events. Calculate the slope of the freezing cycle curve according to the gait freezing index. The specific operation is to fit the freezing cycle curve by linear regression method and calculate its slope value. When the slope is greater than 0, it is determined as an increasing trend of gait freezing; when the slope is less than 0, it is determined as a decreasing trend of gait freezing. This determination process is based on the change trend of the freezing cycle curve and can reflect the dynamic change of gait freezing. Combine the increasing trend and decreasing trend of gait freezing to generate gait change trend data. By integrating the characteristic parameters of the increasing and decreasing trends, a comprehensive gait change trend data set is formed, providing a basis for subsequent evaluation. Divide the gait change trend into three intervals of mild, moderate, and severe gait impairment, and mark them with different colors respectively to obtain the gait change impairment color. The specific operation is to divide the gait change trend into three intervals according to the range of the gait freezing index: mild impairment (0 - 33%), moderate impairment (34% - 66%), severe impairment (67% - 100%), and mark them with green, yellow, and red respectively. Map the gait change impairment color to the degree of Parkinson's gait impairment and visualize the degree of gait impairment to generate a gait impairment assessment report. Through visualization technology, map the gait change impairment color to the assessment report to intuitively display the degree of gait impairment of the patient.

[0146] Particularly importantly, step S44 includes the following steps:

[0147] Step S44: Divide the gait change trend into three intervals of mild, moderate, and severe gait impairment, and mark them with different colors respectively to obtain the gait change impairment color;

[0148] Step S441: Divide the gait change trend into gait impairment levels. If the change in gait movement cycle is less than 10%, the change in step length is less than 5%, the difference in left and right step lengths is less than 3%, the change in step width is less than 2 cm, the decrease in gait speed is less than 10%, the gait symmetry index is greater than 0.9, and the joint flexion and extension dispersion is less than 10°, then it is judged as mild gait impairment;

[0149] Step S442: Divide the gait change trend into gait impairment levels. When the change in gait movement cycle is between 10% and 20%, the change in step length is between 5% and 10%, the difference in left and right step lengths is between 3% and 5%, the change in step width is between 2 cm and 4 cm, the decrease in gait speed is between 10% and 20%, the gait symmetry index is between 0.7 and 0.9, and the joint flexion and extension dispersion is between 10° and 20°, then it is judged as moderate gait impairment;

[0150] Step S443: Divide the gait change trend into gait impairment levels. If the change in gait movement cycle is greater than 20%, the change in step length is greater than 10%, the difference in left and right step lengths is greater than 5%, the change in step width is greater than 4 cm, the decrease in gait speed is greater than 20%, the gait symmetry index is less than 0.7, and the joint flexion and extension dispersion is greater than 20°, then it is judged as severe gait impairment;

[0151] Step S444: Mark mild gait impairment as light green, moderate gait impairment as yellow, and severe gait impairment as red to obtain the color of gait change impairment.

[0152] In an embodiment of the present invention, a high-precision gait analysis system, such as the GAITRite electronic carpet system, is used in combination with a wearable inertial sensor. The GAITRite system can record the time-space parameters of gait in real time, including gait motion cycle, step length, step width, gait speed, etc.; the inertial sensor is used to measure the change of joint angle to obtain the discreteness of joint flexion and extension. The subject walks on the GAITRite electronic carpet with a natural gait, and the system automatically records the gait data. At the same time, the inertial sensor worn by the subject synchronously collects the joint angle data. During the collection process, the integrity and accuracy of the data are ensured to avoid data loss due to equipment failure or abnormal walking of the subject. The time-space parameters collected by the GAITRite system are time-aligned with the joint angle data collected by the inertial sensor to ensure the consistency of the two sets of data in time. The joint angle data collected by the inertial sensor is filtered to remove high-frequency noise and retain effective joint angle change information. A low-pass filter is used with a cutoff frequency set to 10 Hz to smooth the data and reduce interference. The timestamps of the start and end points of each step are extracted from the GAITRite system to calculate the duration of the gait cycle. Based on the footprint position recorded by the GAITRite system, measure the straight-line distance between the starting and ending points of each step. Calculate the stride length of the left and right feet separately, and find the ratio of the difference between the two to the average stride length. Step width: measure the horizontal distance between the center points of the two feet. Gait speed: determine the ratio of step length to gait cycle Gait symmetry index: compare the ratio of the difference in gait parameters of the left and right feet to the sum. Joint flexion and extension dispersion: extract the standard deviation of joint angle changes from inertial sensor data. Mild impairment: when the gait movement cycle changes less than 10%, the step length changes less than 5% and the difference between the left and right step lengths is less than 3%, the step width changes less than 2cm, the gait speed decreases less than 10%, the gait symmetry index is greater than 0.9, and the joint flexion and extension dispersion is less than 10°, it is marked as light green. Moderate impairment: When the gait cycle changes between 10% and 20%, the step length changes between 5% and 10% and the difference between the left and right step lengths is between 3% and 5%, the step width changes between 2 cm and 4 cm, the gait speed decreases between 10% and 20%, the gait symmetry index is between 0.7 and 0.9, and the joint flexion and extension discreteness is between 10° and 20°, it is marked as yellow. Severe impairment: When the gait cycle changes by more than 20%, the step length changes by more than 10% and the difference between the left and right step lengths is more than 5%, the step width changes by more than 4 cm, the gait speed decreases by more than 20%, the gait symmetry index is less than 0.7, and the joint flexion and extension discreteness is greater than 20°, it is marked as red. Use Python's Matplotlib library or professional gait analysis software (such as the analysis software provided by GAITRite) for data visualization. Color marking: According to the degree of impairment, the gait data is marked with different colors in the visualization interface. Mildly damaged areas are marked in light green, moderately damaged areas are marked in yellow, and severely damaged areas are marked in red.Result display: Generate the time-domain curve graph and heat map of gait parameters to visually display the changing trend of gait impairment degree.

[0153] The present invention also provides a Parkinson's disease gait impairment assessment model for the above-mentioned method for establishing a Parkinson's disease gait impairment assessment. The Parkinson's disease gait impairment assessment model includes:

[0154] An image monitoring module for continuously monitoring the gait images of Parkinson's disease patients; when a gait continuity interruption of the gait image is detected, it is determined as a gait freezing event, and the freezing event characteristics, freezing occurrence time period, and freezing duration of the gait freezing event are recorded;

[0155] A gait feature curve construction module for determining gait feature parameters based on gait images; extracting the gait spatio-temporal feature parameters of the gait feature parameters, and constructing a gait feature curve according to the gait spatio-temporal feature parameters; identifying the precursor attributes of the freezing event characteristics according to the gait feature curve to obtain the freezing event precursor attributes;

[0156] A gait freezing quantification module for classifying the freezing event precursor attributes into gait gradual change types; detecting the gait freezing cycle for the gait gradual change types according to the freezing occurrence time period to generate a gait freezing cycle; quantifying the freezing cumulative frequency of the gait freezing cycle based on the freezing duration to obtain a gait freezing index;

[0157] An impairment degree assessment module for determining the gait change trend based on the freezing cycle data and the gait freezing index, and assessing the Parkinson's disease gait impairment degree for the gait change trend to generate a gait impairment assessment report.

[0158] The image monitoring module of the present invention uses a high-resolution image acquisition device to monitor the gait of Parkinson's disease patients in real time, ensuring that a complete gait image sequence can be captured at any time point, continuously recording the walking process of the patient, and providing a comprehensive data basis for subsequent analysis; analyzing the gait images based on image processing algorithms, when a gait continuity interruption is detected, it is automatically determined as a gait freezing event. At the same time, the characteristics of the freezing event are recorded, including the time period when the freezing occurs, the duration of the freezing, and the morphological characteristics of the freezing event, ensuring the accuracy and integrity of the data and avoiding errors caused by manual intervention. Through the gait feature curve construction module, gait spatio-temporal feature parameters are extracted from the gait images, including key parameters such as step length, step width, walking speed, and gait cycle. These parameters are calculated through image analysis algorithms, ensuring the objectivity and repeatability of the data. Based on the extracted gait spatio-temporal feature parameters, a gait feature curve is constructed, with time as the horizontal axis and gait feature parameters as the vertical axis, which can intuitively reflect the change trend of gait parameters over time. And through this curve processing, the system can capture the dynamic process of gait changes; by analyzing the gait feature curve, the characteristic changes before the occurrence of the freezing event are identified, that is, the precursor attributes of the freezing event. This identification process is based on the morphological analysis of the curve and the change trend of the parameters, and can accurately locate the precursor characteristics of the freezing event. Through the gait freezing quantification module, the precursor attributes of the freezing event are divided into different gait gradual change types. This division is based on the morphological characteristics and parameter change rules of the gait feature curve, and can classify complex gait changes; and according to the time period when the freezing occurs, periodic detection of the gait gradual change types is carried out. By analyzing the periodic changes of the gait feature curve, the periodic pattern of gait freezing can be accurately identified, thus revealing the regularity of the gait freezing event; quantitative analysis of the gait freezing cycle is carried out based on the freezing duration, and it is obtained by calculating the weighted sum of the cumulative frequency and the duration of the freezing event, which can comprehensively reflect the severity of gait freezing and provide a unified quantitative standard for the assessment of gait impairment degree. Through the impairment degree assessment module, based on the freezing cycle data and the gait freezing index, the trend of gait changes is analyzed through a mathematical model, and the regularity of the freezing cycle and the change trend of the freezing index can be comprehensively considered, so as to accurately judge the overall situation of gait impairment; according to the trend of gait changes, a quantitative assessment of the gait impairment degree is carried out. This assessment process is based on a preset quantitative standard, and by calculating the difference between the gait freezing index and the normal gait parameters, an objective and quantitative assessment result can be provided; according to the assessment result, a detailed gait impairment assessment report is generated. The report includes detailed records of the freezing event, gait feature curves, analysis results of the freezing cycle, and quantitative assessment of the gait impairment degree. The report is presented in the form of charts and data, which can intuitively display the detailed situation of gait changes and provide comprehensive data support for relevant research.Therefore, through data processing technology and image processing technology, the present invention realizes gait monitoring for Parkinson's disease patients and identifies the characteristics of gait freezing, so as to improve the accuracy of Parkinson's disease gait impairment assessment and shorten the time used in the impairment assessment process.

[0159] A computer-readable storage medium stores a computer program, wherein the computer program is used to execute the established method for assessing Parkinson's disease gait impairment.

[0160] Therefore, from any perspective, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the application documents are intended to be encompassed within the present invention.

[0161] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features invented herein.

Claims

1. A device for assessing gait impairment in Parkinson's disease, characterized in that: Includes the following modules: An image monitoring module is used to continuously monitor the gait images of Parkinson's patients; when a gait continuity interruption in the gait image is detected, it is determined as a gait freezing event, and the freezing event characteristics, freezing occurrence time period and freezing duration of the gait freezing event are recorded; A gait characteristic curve construction module is used to determine gait characteristic parameters based on gait images; extract gait spatiotemporal characteristic parameters of the gait characteristic parameters, and construct a gait characteristic curve according to the gait spatiotemporal characteristic parameters; identify the precursor attribute of the freezing event feature according to the gait characteristic curve to obtain the precursor attribute of the freezing event; the identifying the precursor attribute of the freezing event feature according to the gait characteristic curve includes: On the gait characteristic curve, mark the time point when the gait speed drops below 0.5 m / s as the starting point of the speed freezing event; calculate the rate of change of gait speed within 3 seconds before and after the marked point based on the starting point of the speed freezing event. If the rate of change is less than -0.2 m / s², it is identified as a speed precursor feature; On the gait characteristic curve, mark the time point when the gait symmetry index drops below 0.8 as the starting point of the symmetry freezing event; compare the change in gait symmetry within 5 seconds before and after the marked point based on the starting point of the symmetry freezing event. If the symmetry change exceeds 0.2, record the time interval of the gait symmetry change. If the interval is less than 1 second, it is identified as a symmetry precursor feature. On the gait characteristic curve, mark the time point when the stride length is shortened to less than 68 cm as the starting point of the stride length freezing event; compare the change in stride length within 3 seconds before and after the marked point based on the starting point of the stride length freezing event. If the stride length is shortened by more than 5 cm, it is identified as a stride length precursor feature; On the gait characteristic curve, mark the time point when the step width changes by more than 3.5 cm as the starting point of the step width freezing event; compare the change of step width within 3 seconds before and after the marked point based on the starting point of the step width freezing event. If the step width changes by more than 2 cm, it is identified as a step width precursor feature; On the gait characteristic curve, mark the time point when the joint flexion and extension discreteness changes by more than 10% as the starting point of the flexion and extension freezing event; compare the change of joint flexion and extension discreteness within 3 seconds before and after the marked point based on the starting point of the flexion and extension freezing event. If the change exceeds 5%, it is identified as the precursor feature of joint flexion and extension; The speed precursor feature, symmetry precursor feature, step width precursor feature and joint flexion and extension precursor feature are combined to obtain the freezing event precursor attribute; The gait freezing quantification module is used to classify the precursor attributes of the freezing event into gait gradual change types; perform gait freezing cycle detection on the gait gradual change types according to the freezing time period to generate the gait freezing cycle; perform freezing cumulative frequency quantification on the gait freezing cycle based on the freezing duration to obtain the gait freezing index; The impairment degree assessment module is used to determine the gait change trend based on the freezing cycle data and the gait freezing index, and to assess the gait impairment degree of Parkinson's disease on the gait change trend, and to generate a gait impairment assessment report.

2. The device for assessing gait impairment in Parkinson's disease according to claim 1, characterized in that: The image monitoring module is used to perform the following steps: Step S11: setting the frame rate of the binocular camera to 40-60 frames / second, the resolution to 1920×1080 pixels, and setting the angle between the binocular camera and the patient's walking path to 45°; Step S12: collecting the complete cycle of each walking of the patient, including the initial gait, the middle gait and the final gait, and each collection lasts for 3 minutes; Step S13: activating the automatic tracking function of the binocular camera to continuously monitor the walking path, number of steps, walking speed and walking movements of the Parkinson's disease patient to obtain a gait image; Step S14: recording the number of swings in the patient's gait image, and marking the number of swings in the patient's gait as zero for two consecutive cycles; The gait interruption point is determined for the case of two consecutive cycles with zero times, and the gait continuity interruption data is obtained; Step S15: performing gait freezing judgment on the gait image according to the gait continuity interruption data, obtaining a gait freezing event, and recording the freezing event characteristics, freezing occurrence time period and freezing duration of the gait freezing event.

3. The device for assessing gait impairment in Parkinson's disease according to claim 1, characterized in that: Determining gait characteristic parameters based on the gait image comprises: Divide the gait image into a plurality of continuous frame sequences, wherein each frame sequence corresponds to a gait cycle; In each frame sequence, the foot joint, knee joint and ankle joint are extracted to obtain the human joint point information; the displacement time change of the human joint point information in adjacent frames is calculated to generate the gait motion cycle; Calculate the distance between the foot joint and the contact point in two consecutive gait motion cycles to obtain the step length data; measure the lateral distance between the left and right foot joints and the contact point to obtain the step width data; Calculate gait speed using step length data and gait motion cycle; determine gait symmetry for gait motion cycle based on gait speed and step width data; Calculate the flexion and extension phase angles of the knee joint and the ankle joint in two consecutive gait motion cycles, and map the flexion and extension phase angles to flexion and extension discreteness to obtain joint flexion and extension discreteness; The gait motion cycle, step length data, step width data, gait speed, gait symmetry and joint flexion and extension discreteness are combined into gait characteristic parameters.

4. The device for assessing gait impairment in Parkinson's disease according to claim 3, characterized in that: The step of extracting the gait spatiotemporal characteristic parameters of the gait characteristic parameters and constructing a gait characteristic curve according to the gait spatiotemporal characteristic parameters comprises: Extracting the periodic time information of the gait characteristic parameters, and dividing the periodic time information into a time period sequence; performing sequence parameterization on the time period sequence to obtain the time period sequence parameters; Based on the time period sequence parameters, gait spatial feature recognition is performed on gait feature parameters, and feature parameters of gait spatial features are quantified to obtain time period sequence parameters; Arrange the time period series parameters in chronological order to form chronological order data; The time-arranged sequence data is used as the horizontal axis and the time period sequence parameters are used as the vertical axis to construct the initial gait characteristic curve; The initial gait characteristic curve is processed for curve smoothness to generate a gait characteristic curve.

5. The device for assessing gait impairment in Parkinson's disease according to claim 1, characterized in that: The Gait Freezing Quantification module is used to perform the following steps: Step S31: extracting gait interruption precursor features from the freeze event precursor attributes to obtain gait interruption precursor features; Determine the interruption type of the precursor features of gait interruption and generate the gait interruption type; Step S32: performing inter-type similarity comparison on the gait interruption types to obtain inter-type similarity data; The precursor attributes of freezing events are divided into gait gradient types according to the similar data between types; Step S33: segmenting the freezing time period according to the freezing event characteristics, taking the freezing event characteristic occurrence point as the center, extending forward and backward by 5 seconds each, and dividing it into a pre-freezing period and a post-freezing period; Step S34: marking the gait type normal interval according to the pre-freezing interval for the gait gradual change type; marking the gait type frozen interval according to the post-freezing interval; Step S35: gait freezing period is calculated based on the normal gait type interval and the gait type freezing interval to generate a gait freezing period; Step S36: quantifying the cumulative freezing frequency of the gait freezing period based on the freezing duration to obtain a gait freezing index.

6. The device for assessing gait impairment in Parkinson's disease according to claim 5, characterized in that: Step S36 includes the following steps: Step S361: performing periodic segmentation processing on the freezing duration to obtain the freezing type segmentation duration; Step S362: performing duration normalization processing on the frozen type segmentation duration to obtain duration normalized data; Step S363: performing freezing frequency statistics on the gait freezing period according to the normalized duration data, and determining the occurrence frequency of each freezing period to obtain freezing frequency distribution data; Step S364: performing cumulative calculation on the freezing frequency distribution data, and accumulating the frequencies of each freezing period in chronological order to form a freezing cumulative frequency curve; Step S365: performing frozen frequency parameter mapping on the frozen cumulative frequency curve, and dividing the frozen frequency parameter into a plurality of quantization intervals, each interval corresponding to a quantization value, to generate a frozen frequency quantization parameter; Step S366: performing weighted calculation on the freezing frequency quantization parameters to obtain a final gait freezing index.

7. The device for assessing gait impairment in Parkinson's disease according to claim 1, characterized in that: The damage assessment module is used to perform the following steps: Step S41: Arrange the freezing cycle data in chronological order, and draw a freezing cycle curve with the start time of the freezing cycle as the horizontal axis and the freezing duration as the vertical axis; Step S42: Calculate the slope of the freezing cycle curve according to the gait freezing index, and when the slope is greater than 0, determine that the gait freezing is increasing; When the slope is less than 0, it is judged as a trend of weakening gait freezing; Step S43: merging the gait freezing enhancement trend and the gait freezing reduction trend into gait trend features to generate gait change trend data; Step S44: dividing the gait change trend into three intervals of mild, moderate and severe gait impairment, and marking them with different colors to obtain gait change impairment colors; Step S45: Mapping the color of the gait change impairment to the degree of gait impairment of Parkinson's disease, and visualizing the degree of gait impairment to generate a gait impairment assessment report.

Images