Fine-grained hip-knee joint coordination assessment method, device and system

Abstract

The present invention provides a fine-grained hip-knee joint coordination evaluation method, device and system, which belongs to the field of disease diagnosis technology, wherein the method includes: determining a reference hip-knee joint angle cycle diagram and a reference plantar pressure curve diagram of a healthy person, obtaining a target hip-knee joint angle cycle diagram and a target plantar pressure curve diagram of a patient; calculating a global shape deviation evaluation value of the target hip-knee joint angle cycle diagram based on a dynamic time planning-shape context algorithm; dividing the target hip-knee joint angle cycle diagram into multiple gait phases based on a target plantar pressure curve diagram; calculating a shape deviation evaluation value of a target sub-hip-knee joint angle cycle diagram of each gait phase based on a dynamic time planning-shape context algorithm; and evaluating the patient's hip-knee joint coordination according to the global shape deviation evaluation value and the shape deviation evaluation value of each gait phase. The present invention can perform a fine-grained evaluation of hip-knee joint coordination, thereby improving the accuracy of the evaluation.

Description

Technical Field

[0001] The present invention relates to the technical field of disease diagnosis, and in particular to a fine-grained hip and knee joint coordination assessment method, device and system. Background Art

[0002] Gait assessment is a method of diagnosing diseases by observing and analyzing individual walking patterns. Gait assessment can help doctors or researchers identify the severity and cause of gait abnormalities and provide a basis for developing personalized treatment plans. At present, the existing hip and knee coordination assessment methods based on cyclic graph moment representation, vector encoding and other technologies only focus on global features, lose some key gait characteristics, and affect the accuracy of hip and knee coordination assessment. Summary of the invention

[0003] The present invention provides a fine-grained hip-knee joint coordination assessment method, device and system to solve the defects of the hip-knee joint coordination assessment methods in the prior art based on cyclic graph moment representation, vector encoding and other technologies, which only focus on global features, lose certain key gait characteristics, and affect the accuracy of hip-knee joint coordination assessment.

[0004] The present invention provides a fine-grained hip and knee joint coordination assessment method, comprising:

[0005] Determine a reference hip-knee joint angle cycle diagram and a reference plantar pressure curve diagram of a healthy person in each gait cycle, and obtain a target hip-knee joint angle cycle diagram and a target plantar pressure curve diagram of a patient in each gait cycle;

[0006] Based on the dynamic time planning-shape context algorithm, a shape deviation evaluation value between the target hip and knee joint angle cycle graph and the reference hip and knee joint angle cycle graph is calculated to obtain a global shape deviation evaluation value;

[0007] Based on the reference plantar pressure curve graph, dividing the reference hip-knee joint angle cycle graph into a plurality of reference sub-hip-knee joint angle cycle graphs of a plurality of gait phases; based on the target plantar pressure curve graph, dividing the target hip-knee joint angle cycle graph into a plurality of target sub-hip-knee joint angle cycle graphs of a plurality of gait phases;

[0008] Based on the dynamic time planning-shape context algorithm, the shape deviation evaluation value between the target sub-hip and knee joint angle cycle diagram and the corresponding reference sub-hip and knee joint angle cycle diagram of each gait phase is calculated to obtain the shape deviation evaluation value of each gait phase;

[0009] The patient's hip and knee joint coordination is evaluated based on the global shape deviation evaluation value and the shape deviation evaluation value of each gait phase to obtain an evaluation result.

[0010] In some embodiments, the plurality of gait phases include early stance, mid-stance, end-stance, and swing phase.

[0011] In some embodiments, the shape deviation evaluation value between the target sub-hip and knee joint angle cycle diagram and the corresponding reference sub-hip and knee joint angle cycle diagram of each gait phase is calculated based on the dynamic time planning-shape context algorithm to obtain the shape deviation evaluation value of each gait phase, including:

[0012] Based on the dynamic time planning algorithm, the shortest matching path between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase is calculated to obtain the shortest matching path of each gait phase, and the shortest matching path of each gait phase is visualized;

[0013] Based on the dynamic time planning-shape context algorithm, a cost matrix between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase is calculated to obtain the cost matrix of each gait phase;

[0014] According to the shortest matching path of each gait phase and the cost matrix of each gait phase, the shape deviation evaluation value between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase is calculated to obtain the shape deviation evaluation value of each gait phase.

[0015] In some embodiments, the step of calculating the shortest matching path between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase to obtain the shortest matching path of each gait phase includes:

[0016] Calculate the distance matrix between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase to obtain the distance matrix of each gait phase;

[0017] Based on the distance matrix of each gait phase, a cumulative cost matrix between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase is calculated to obtain a cumulative cost matrix of each gait phase;

[0018] Determine the boundary conditions, and based on the cumulative cost matrix of each gait phase and the boundary conditions, calculate the shortest matching path between the target sub-hip and knee joint angle cycle graph of each gait phase and the reference sub-hip and knee joint angle cycle graph of each gait phase to obtain the shortest matching path of each gait phase.

[0019] In some embodiments, the cost matrix between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase is calculated to obtain the cost matrix of each gait phase, including:

[0020] Calculate a reference distance matrix and a reference angle matrix of the reference sub-hip and knee joint angle cycle diagram of each gait phase, and calculate a reference histogram matrix of the reference sub-hip and knee joint angle cycle diagram of each gait phase based on the reference distance matrix and the reference angle matrix;

[0021] Calculate the target distance matrix and target angle matrix of the target sub-hip and knee joint angle cycle diagram of each gait phase, and calculate the target histogram matrix of the target sub-hip and knee joint angle cycle diagram of each gait phase based on the target distance matrix and target angle matrix;

[0022] Based on the target histogram matrix and the reference histogram matrix, a cost matrix between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase is calculated.

[0023] In some embodiments, the shape deviation evaluation value between the target hip and knee joint angle cycle graph and the reference hip and knee joint angle cycle graph is calculated based on the dynamic time planning-shape context algorithm to obtain a global shape deviation evaluation value, including:

[0024] Based on a dynamic time planning algorithm, the shortest matching path between the target hip-knee joint angle cycle diagram and the reference hip-knee joint angle cycle diagram is calculated to obtain a global shortest matching path, and the global shortest matching path is visualized;

[0025] Based on the dynamic time planning-shape context algorithm, a cost matrix between the target hip and knee joint angle cycle graph and the reference hip and knee joint angle cycle graph is calculated to obtain a global cost matrix;

[0026] According to the global shortest matching path and the global cost matrix, a shape deviation evaluation value between the target hip-knee joint angle cycle graph and the reference hip-knee joint angle cycle graph is calculated to obtain the global shape deviation evaluation value.

[0027] In some embodiments, determining a reference hip and knee joint angle cycle diagram and a reference plantar pressure curve diagram of a healthy person in each gait cycle includes:

[0028] Acquire a first lower limb kinematics video and first plantar pressure data of a healthy person in each gait cycle, and obtain first hip joint angle data and first knee joint angle data based on the first lower limb kinematics video;

[0029] Determining the reference hip and knee joint angle cycle diagram according to the first hip joint angle data and the first knee joint angle data;

[0030] The reference plantar pressure curve graph is determined according to the first plantar pressure data.

[0031] In some embodiments, the step of obtaining a target hip and knee joint angle cycle diagram and a target plantar pressure curve diagram of the patient in each gait cycle includes:

[0032] Acquire a second lower limb kinematics video and second plantar pressure data of the patient in each gait cycle, and obtain second hip joint angle data and second knee joint angle data based on the second lower limb kinematics video;

[0033] generating the target hip and knee joint angle cycle diagram based on the second hip joint angle data and the second knee joint angle data;

[0034] The target plantar pressure curve graph is generated based on the second plantar pressure data.

[0035] The present invention also provides a fine-grained hip-knee joint coordination assessment device, comprising:

[0036] An acquisition unit is used to determine a reference hip and knee joint angle cycle diagram and a reference plantar pressure curve diagram of a healthy person in each gait cycle, and to acquire a target hip and knee joint angle cycle diagram and a target plantar pressure curve diagram of a patient in each gait cycle;

[0037] A first calculation unit is used to calculate a shape deviation evaluation value between the target hip and knee joint angle cycle graph and the reference hip and knee joint angle cycle graph based on a dynamic time planning-shape context algorithm to obtain a global shape deviation evaluation value;

[0038] a dividing unit, for dividing the reference hip-knee joint angle cycle diagram into a plurality of reference sub-hip-knee joint angle cycle diagrams of a plurality of gait phases based on the reference plantar pressure curve diagram, and for dividing the target hip-knee joint angle cycle diagram into a plurality of target sub-hip-knee joint angle cycle diagrams of a plurality of gait phases based on the target plantar pressure curve diagram;

[0039] A second calculation unit is used to calculate a shape deviation evaluation value between a target sub-hip and knee joint angle cycle diagram and a corresponding reference sub-hip and knee joint angle cycle diagram for each gait phase based on a dynamic time planning-shape context algorithm to obtain a shape deviation evaluation value for each gait phase;

[0040] The evaluation unit is used to evaluate the patient's hip and knee joint coordination according to the global shape deviation evaluation value and the shape deviation evaluation value of each gait phase to obtain an evaluation result.

[0041] The present invention also provides a fine-grained hip-knee coordination assessment system, comprising: a binocular near-infrared camera, an RGB camera, a video capture module, a plantar pressure sensor, and the above-mentioned fine-grained hip-knee coordination assessment device;

[0042] The binocular near-infrared camera is used to record black-and-white video of the movement of human lower limbs;

[0043] The RGB camera is used to visualize and record color video of human lower limb movements;

[0044] The video capture module is used to receive the black-and-white video of the human lower limb movement and the color video of the human lower limb movement to generate a lower limb kinematics video, and send the lower limb kinematics video to the fine-grained hip and knee coordination assessment device;

[0045] The plantar pressure sensor is used to collect plantar pressure data of a human body and send the plantar pressure data to the fine-grained hip-knee joint coordination assessment device.

[0046] The present invention provides a fine-grained hip-knee joint coordination assessment method, device and system. The method determines a reference hip-knee joint angle cycle diagram and a reference plantar pressure curve diagram of a healthy person, obtains a target hip-knee joint angle cycle diagram and a target plantar pressure curve diagram of a patient, calculates a global shape deviation assessment value between the target hip-knee joint angle cycle diagram and the reference hip-knee joint angle cycle diagram based on a dynamic time planning-shape context algorithm, divides the reference hip-knee joint angle cycle diagram into multiple gait phases based on the reference plantar pressure curve diagram, divides the target hip-knee joint angle cycle diagram into multiple gait phases based on the target plantar pressure curve diagram, calculates a shape deviation assessment value between a target sub-hip-knee joint angle cycle diagram of each gait phase and a corresponding reference sub-hip-knee joint angle cycle diagram based on a dynamic time planning-shape context algorithm, performs a global assessment and a fine-grained assessment of the patient's hip-knee joint coordination based on the global shape deviation assessment value and the shape deviation assessment value of each gait phase, and improves the accuracy of the hip-knee joint coordination assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 is a flow chart of a fine-grained hip-knee joint coordination assessment method provided by an embodiment of the present invention;

[0049] Figure 2 is a cyclic diagram of a reference hip-knee joint angle and a target hip-knee joint angle provided by an embodiment of the present invention;

[0050] Figure 3 It is a schematic diagram of a flow chart for calculating a shape deviation evaluation value between a target sub-hip and knee joint angle cycle diagram and a corresponding reference sub-hip and knee joint angle cycle diagram for each gait phase provided by an embodiment of the present invention.

[0051] Figure 4 It is a schematic diagram of the structure of a fine-grained hip-knee joint coordination assessment device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] The terms "first", "second", etc. in the present invention are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present invention can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more.

[0054] It should be noted that an embodiment of the present invention provides a fine-grained hip and knee joint coordination assessment system, which specifically includes: a binocular near-infrared camera, an RGB camera, a computer equipped with a video capture module, an insole provided with a plantar pressure sensor and a fine-grained hip and knee joint coordination assessment device. The computer is communicatively connected with the binocular near-infrared camera, the RGB camera and the plantar pressure sensor. In addition, the system proposed in the present invention also includes a near-infrared light source and a power supply.

[0055] Among them, the binocular near-infrared camera is used to record black-and-white video of human lower limb movement; the RGB camera is used to visualize and record color video of human lower limb movement; the computer equipped with a video capture module is used to receive black-and-white video of human lower limb movement and color video of human lower limb movement to generate lower limb kinematic video; the plantar pressure sensor is used to collect plantar pressure data of the human body and send the plantar pressure data to the computer.

[0056] The power supply can power the computer and the light source at the same time. The light source is composed of two circular light arrays and is installed around the two lenses of the binocular camera. The light source can emit 850nm infrared light evenly, and it is equipped with a brightness adjustment knob. The intensity of the infrared light can be manually adjusted according to the brightness of the environment, thereby adjusting the clarity of the marker points in the image frame of the human lower limb movement video.

[0057] Among them, multiple plantar pressure sensor arrays are evenly arranged on the insole to collect pressure data of different areas of the human sole.

[0058] In practical applications, the binocular near-infrared camera can support different frame rates and resolutions of video capture formats to record black and white videos of human lower limb movement. When the resolution is 720p, the video capture frame rate can reach up to 60FPS. The RGB camera visualizes and records the color video of human lower limb movement at a video capture frame rate of 60FPS. The video recording module in the computer can be equipped with Directs Show video recording software, in which the video recording module can simultaneously record the human lower limb movement videos from the RGB camera and the binocular near-infrared camera. The computer can also control the opening of the two cameras, the recording, termination and saving of the video through the video recording module.

[0059] First, preparation work is required before data collection. Reflective markers are attached to the key joints of the patient's lower limbs (such as the hip and knee joints) and the insoles to ensure the accuracy of motion capture. Then, the video capture module, binocular near-infrared camera, RGB camera, plantar pressure sensor and near-infrared light source of the computer are started in sequence. The position of the camera is adjusted until the images of the near-infrared camera and the RGB camera can capture the range of motion of the subject's lower limbs. The brightness of the light source is manually adjusted through the image in the near-infrared camera until the reflective marker ball can be retained to the maximum extent in the image and the interference of other reflective objects is excluded. The video of the RGB camera and the near-infrared camera is started to be recorded through the video capture module, and the plantar pressure data collected by the plantar pressure sensor is stored through the computer.

[0060] Secondly, during the data collection process, static anatomical calibration was performed. The patients were asked to stand still in a T-position for 1 second. Then, they were asked to walk along a 20-meter-long trail at a comfortable speed of their own choice. Each walking time was controlled at about 10 seconds. The video of the patient's lower limb movement in each gait cycle was recorded to obtain the patient's hip and knee joint kinematic data (such as hip joint angle, knee joint angle, etc.), capture the patient's plantar pressure distribution in detail in each gait cycle, and record the plantar pressure data. Taking into account the speed-dependent characteristics of walking gait, healthy people were asked to walk on the treadmill at a controllable and comfortable walking speed for one minute, and the video of the healthy people's lower limb movement and plantar pressure data were recorded.

[0061] In addition, in this embodiment, after the video capture module generates the lower limb kinematics video, it sends the lower limb kinematics video to the fine-grained hip-knee joint coordination assessment device, so that the fine-grained hip-knee joint coordination assessment device performs a fine-grained hip-knee joint coordination assessment based on the lower limb kinematics video. The video capture module and the fine-grained hip-knee joint coordination assessment device can be installed in the same computer or in different computers, and the present invention does not limit this.

[0062] Figure 1 FIG. 1 is a flow chart of a fine-grained hip-knee joint coordination assessment method provided by an embodiment of the present invention. Figure 1 As shown, a fine-grained hip-knee coordination assessment method is provided, comprising the following steps: step 110, step 120, step 130, step 140 and step 150. The method flow steps are only used as a possible implementation of the present invention.

[0063] Step 110, determine the reference hip and knee joint angle cycle diagram and the reference plantar pressure curve diagram of a healthy person in each gait cycle, and obtain the target hip and knee joint angle cycle diagram and the target plantar pressure curve diagram of the patient in each gait cycle.

[0064] Among them, the hip-knee joint angle cycle diagram is also called the hip angle-knee angle diagram, which is used to describe the angle changes of the hip and knee joints during the gait cycle.

[0065] The gait cycle refers to the process of the same foot from the heel leaving the ground to the heel landing again when walking.

[0066] Figure 2 A cycle diagram of a reference hip-knee joint angle and a target hip-knee joint angle provided by an embodiment of the present invention. Figure 2 As shown, the solid line represents the reference hip and knee joint angle cycle diagram of a healthy person in each gait cycle, and the dotted line represents the target hip and knee joint angle cycle diagram of a patient in each gait cycle.

[0067] In some embodiments, determining a reference hip and knee joint angle cycle diagram and a reference plantar pressure curve diagram of a healthy person in each gait cycle includes:

[0068] Acquire a first lower limb kinematics video and first plantar pressure data of a healthy person in each gait cycle, and obtain first hip joint angle data and first knee joint angle data based on the first lower limb kinematics video;

[0069] Determine a reference hip and knee joint angle cycle diagram according to the first hip joint angle data and the first knee joint angle data;

[0070] A reference plantar pressure curve graph is determined according to the first plantar pressure data.

[0071] Optionally, obtain the first lower limb kinematics video of a healthy person in multiple gait cycles, obtain the first hip joint angle data and the first knee joint angle data of the multiple gait cycles based on the first lower limb kinematics video in the multiple gait cycles, calculate the average value thereof, and obtain the first hip joint angle data and the first knee joint angle data of each gait cycle.

[0072] Optionally, the first plantar pressure data of a healthy person in multiple gait cycles is acquired, and the average value thereof is calculated to obtain the first plantar pressure data of each gait cycle.

[0073] Optionally, the first lower limb kinematics video is processed to obtain first original hip joint angle data and first original knee joint angle data, and the first original hip joint angle data and the first original knee joint angle data are preprocessed to obtain first hip joint angle data and first knee joint angle data.

[0074] In some embodiments, obtaining a target hip and knee joint angle cycle diagram and a target plantar pressure curve diagram of the patient in each gait cycle includes:

[0075] Acquire a second lower limb kinematics video and second plantar pressure data of the patient in each gait cycle, and obtain second hip joint angle data and second knee joint angle data based on the second lower limb kinematics video;

[0076] generating a target hip and knee joint angle cycle diagram based on the second hip joint angle data and the second knee joint angle data;

[0077] A target plantar pressure curve graph is generated based on the second plantar pressure data.

[0078] Optionally, obtain the patient's second lower limb kinematics video during multiple gait cycles, obtain the second hip joint angle data and the second knee joint angle data for multiple gait cycles based on the second lower limb kinematics video during multiple gait cycles, calculate the average value thereof, and obtain the second hip joint angle data and the second knee joint angle data for each gait cycle.

[0079] Optionally, the second plantar pressure data of the patient in multiple gait cycles is acquired, and the average value thereof is calculated to obtain the second plantar pressure data of each gait cycle.

[0080] Optionally, the second lower limb kinematics video is processed to obtain second original hip joint angle data and second original knee joint angle data, and the second original hip joint angle data and the second original knee joint angle data are preprocessed to obtain second hip joint angle data and second knee joint angle data.

[0081] Step 120: Based on the dynamic time planning-shape context algorithm, calculate the shape deviation evaluation value between the target hip and knee joint angle cycle graph and the reference hip and knee joint angle cycle graph to obtain a global shape deviation evaluation value.

[0082] It should be noted that the Dynamic Time Warping (DTW) algorithm is an algorithm used to calculate the similarity between two time series, and the Shape Context (SC) algorithm is an algorithm used to describe shapes. It identifies shapes by comparing the relative positions of key points. The DTW algorithm is combined with the SC algorithm to obtain the DTW-SC algorithm.

[0083] In some embodiments, in step 120, based on the dynamic time planning-shape context algorithm, the shape deviation evaluation value between the target hip and knee joint angle cycle graph and the reference hip and knee joint angle cycle graph is calculated to obtain a global shape deviation evaluation value, including the following steps: step 121, step 122 and step 123.

[0084] Step 121: Based on the dynamic time planning algorithm, calculate the shortest matching path between the target hip-knee joint angle cycle diagram and the reference hip-knee joint angle cycle diagram, obtain the global shortest matching path, and visualize the global shortest matching path.

[0085] Optionally, based on a dynamic time planning algorithm, a distance matrix between a target hip and knee joint angle cycle graph (ie, cycle graph B) and a reference hip and knee joint angle cycle graph (ie, cycle graph A) is calculated.

[0086] Optionally, the Euclidean distances between the sample points in the cycle graph A and the sample points in the cycle graph B are calculated according to the distance matrix.

[0087] Optionally, let set A be the set of sample points in cycle graph A, set B be the set of sample points in cycle graph B, and the dimension of each sample point is (i.e., each sample point contains two components of the hip and knee joint angles), each pair of sample points and The calculation formula of the Euclidean distance between is as follows:

[0088] ;

[0089] in, Indicates the first The sample points and the The Euclidean distance of sample points is Indicates the first The hip joint angle of the sample points, Indicates the first The knee joint angle of the sample points, represents the first The hip joint angle of the sample points, represents the first The knee joint angle of each sample point.

[0090] Optionally, a cumulative cost matrix between the cycle graph A and the cycle graph B is calculated, and the cumulative cost matrix is ​​constructed recursively.

[0091] Optionally, the cumulative cost matrix is ​​defined as:

[0092] ;

[0093] in, represents the cumulative cost of the i-th sample point in set A and the j-th sample point in set B, represents the cumulative cost of the i-1th sample point in set A and the jth sample point in set B, represents the cumulative cost of the i-th sample point in set A and the j-1-th sample point in set B, Represents the cumulative cost of the i-1th sample point in set A and the j-1th sample point in set B.

[0094] The initial conditions are:

[0095] ;

[0096] The boundary conditions are:

[0097] ;

[0098] ;

[0099] It should be noted that by calculating the cumulative cost of each pair of sample points, the minimum matching cost from the starting point to any point can be determined to obtain the cumulative cost matrix.

[0100] Optionally, based on a cumulative cost matrix between the cycle graph A and the cycle graph B, a shortest matching path between the cycle graph A and the cycle graph B is obtained.

[0101] Optionally, starting from the lower right corner of the cumulative cost matrix, backtrack to the starting point in sequence, and choose the direction with the minimum cumulative cost at each step. The expression of the backtracking process is as follows:

[0102] ;

[0103] Optionally, when backtracking, each step satisfies the following conditions:

[0104] ;

[0105] in, represents the shortest matching path, that is, the optimal matching path between cycle graph A and cycle graph B.

[0106] It can be understood that by calculating the shortest matching path between the target hip and knee joint angle cycle diagram and the reference hip and knee joint angle cycle diagram, the global shortest matching path is obtained, which provides a data basis for the global evaluation of hip and knee joint coordination.

[0107] Step 122: Based on the dynamic time planning-shape context algorithm, the cost matrix between the target hip and knee joint angle cycle graph and the reference hip and knee joint angle cycle graph is calculated to obtain a global cost matrix.

[0108] Optionally, based on the dynamic time planning-shape context algorithm, the distance matrix and angle matrix of the target hip and knee joint angle cycle graph are calculated, and the distance matrix and angle matrix of the reference hip and knee joint angle cycle graph are calculated.

[0109] Optionally, a first histogram matrix of the target hip and knee joint angle cycle graph is calculated based on the distance matrix and angle matrix of the target hip and knee joint angle cycle graph.

[0110] Optionally, based on the two-dimensional coordinates of any two sample points in the target hip and knee joint angle cycle graph, the Euclidean distance between the any two sample points is calculated to obtain a distance matrix of the target hip and knee joint angle cycle graph.

[0111] Optionally, according to the two-dimensional coordinates of any two sample points in the target hip and knee joint angle cycle diagram, the angle difference between the any two sample points is calculated to obtain the angle matrix of the target hip and knee joint angle cycle diagram.

[0112] Optionally, the distance matrix and the angle matrix of the target hip and knee joint angle circulant graph are mapped into a first histogram matrix using a log-polar coordinate system.

[0113] Alternatively, the expression of the histogram matrix of the cycle graph B is as follows:

[0114] ;

[0115] in, represents the histogram matrix of the cyclic graph B, represents the distance matrix of the cyclic graph B, Represents the angle matrix of the cyclic graph B.

[0116] Optionally, a second histogram matrix of the reference hip and knee joint angle cycle map is calculated based on the distance matrix and angle matrix of the reference hip and knee joint angle cycle map.

[0117] Optionally, for a sample point in the reference hip and knee joint angle cycle graph, its distance feature vector is divided into 5 blocks, and its angle feature vector is divided into 12 blocks, and the second histogram matrix of the sample point is obtained as follows: .

[0118] Alternatively, the expression of the histogram matrix of the cycle graph A is as follows:

[0119] ;

[0120] in, represents the histogram matrix of the cyclic graph A, represents the distance matrix of the cyclic graph A, Represents the angle matrix of the cyclic graph A.

[0121] Optionally, a cost matrix between the target hip and knee joint angle cycle graph and the reference hip and knee joint angle cycle graph is calculated based on the first histogram matrix and the second histogram matrix.

[0122] Optionally, the cost matrix between the i-th sample point in the cycle graph A and the j-th sample point in the cycle graph B is defined as:

[0123] ;

[0124] in, represents the shape deviation (i.e., cost) between the i-th sample point in the cycle graph A and the j-th sample point in the cycle graph B.

[0125] Step 123: Calculate the shape deviation evaluation value between the target hip-knee joint angle cycle diagram and the reference hip-knee joint angle cycle diagram based on the global shortest matching path and the global cost matrix to obtain a global shape deviation evaluation value.

[0126] Optionally, all target point pairs are determined according to the global shortest matching path, the shape deviation of each target point pair is extracted from the global cost matrix, the mean of the shape deviation of each target point pair is calculated, and the global shape deviation evaluation value is obtained.

[0127] Optionally, the calculation formula of the global shape deviation evaluation value is as follows:

[0128] ;

[0129] in, represents the global shape deviation evaluation value, Indicates the number of target point pairs.

[0130] Step 130: Based on the reference plantar pressure curve graph, divide the reference hip-knee joint angle cycle graph into multiple reference sub-hip-knee joint angle cycle graphs of multiple gait phases; based on the target plantar pressure curve graph, divide the target hip-knee joint angle cycle graph into multiple target sub-hip-knee joint angle cycle graphs of multiple gait phases.

[0131] Among them, gait phase is used to describe the different stages in the gait cycle, including the stance phase and the swing phase. The stance phase refers to the time when the lower limbs contact the ground and bear gravity, and the swing phase refers to the time between the foot leaving the ground and stepping forward to landing again.

[0132] In some embodiments, the multiple gait phases include early stance, mid-stance, end-stance, and swing phase.

[0133] Among them, the swing period is divided into three small phases, namely the early swing period, the middle swing period and the late swing period.

[0134] Among them, the reference sub-hip and knee joint angle cycle diagrams of the four gait phases of the reference hip and knee joint angle cycle diagram (i.e., cycle diagram A) are: A_early_stance (i.e., cycle diagram A in the early support phase), A_mid_stance (i.e., cycle diagram A in the middle support phase), A_late_stance (i.e., cycle diagram A in the late support phase) and A_swing (i.e., cycle diagram A in the swing phase).

[0135] Among them, the target sub-hip and knee joint angle cycle diagrams of the four gait phases of the target hip and knee joint angle cycle diagram (i.e., cycle diagram B) are: B_early_stance (i.e., cycle diagram B in the early support phase), B_mid_stance (i.e., cycle diagram B in the middle support phase), B_late_stance (i.e., cycle diagram B in the late support phase) and B_swing (i.e., cycle diagram B in the swing phase).

[0136] Step 140, based on the dynamic time planning-shape context algorithm, calculate the shape deviation evaluation value between the target sub-hip and knee joint angle cycle diagram and the corresponding reference sub-hip and knee joint angle cycle diagram of each gait phase, and obtain the shape deviation evaluation value of each gait phase;

[0137] Optionally, the dtw_sc_early_stance indicator of curve A_early_stance and curve B_early_stance (i.e., the shape deviation evaluation value in the early support period) is calculated; the dtw_sc_mid_stance indicator of curve A_mid_stance and curve B_mid_stance (i.e., the shape deviation evaluation value in the middle support period) is calculated; the dtw_sc_late_stance indicator of curve A_late_stance and curve B_late_stance (i.e., the shape deviation evaluation value in the late support period) is calculated; the dtw_sc_swing indicator of curve A_swing and curve B_swing (i.e., the shape deviation evaluation value in the swing period) is calculated.

[0138] Figure 3 A schematic diagram of a flow chart for calculating a shape deviation evaluation value between a target sub-hip and knee joint angle cycle diagram and a corresponding reference sub-hip and knee joint angle cycle diagram for each gait phase provided in an embodiment of the present invention.

[0139] like Figure 3 As shown, in some embodiments, in step 140, based on the dynamic time planning-shape context algorithm, a shape deviation evaluation value between the target sub-hip and knee joint angle cycle diagram and the corresponding reference sub-hip and knee joint angle cycle diagram of each gait phase is calculated to obtain a shape deviation evaluation value of each gait phase, including:

[0140] Step 141: Based on the dynamic time planning algorithm, calculate the shortest matching path between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase, obtain the shortest matching path of each gait phase, and visualize the shortest matching path of each gait phase.

[0141] Optionally, calculate the P of curve A_early_stance and curve B_early_stance path_early_stance indicator (i.e. the shortest matching path in the early stage of support); calculate the P of curve A_mid_stance and curve B_mid_stance path _mid_stance indicator (i.e. the shortest matching path for mid-term support); calculate the P of curve A_late_stance and curve B_late_stance path _late_stance indicator (i.e. the shortest matching path at the end of the support); calculate the P of curve A_swing and curve B_swing path _swing indicator (i.e. the shortest matching path during the swing period).

[0142] In some embodiments, the shortest matching path between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase is calculated in step 141 to obtain the shortest matching path of each gait phase, including:

[0143] Step 1411, calculate the distance matrix between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase, and obtain the distance matrix of each gait phase.

[0144] Optionally, distance matrices are calculated for the early support, mid support, late support, and swing phases.

[0145] Step 1412: Based on the distance matrix of each gait phase, calculate the cumulative cost matrix between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase to obtain the cumulative cost matrix of each gait phase.

[0146] Optionally, a cumulative cost matrix is ​​calculated for the early support, mid support, late support, and swing phases.

[0147] Step 1413, determine the boundary conditions, and based on the cumulative cost matrix and boundary conditions of each gait phase, calculate the shortest matching path between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase to obtain the shortest matching path of each gait phase.

[0148] Step 142: Based on the dynamic time planning-shape context algorithm, calculate the cost matrix between the target sub-hip and knee joint angle cycle graph of each gait phase and the reference sub-hip and knee joint angle cycle graph of each gait phase to obtain the cost matrix of each gait phase.

[0149] Optionally, calculate the C of curve A_early_stance and curve B_early_stance sc_early_stance indicator (i.e., the cost matrix supporting the early stage); calculate the C of curve A_mid_stance and curve B_mid_stance sc _mid_stance indicator (i.e., the cost matrix supporting the mid-term); calculate the C of curve A_late_stance and curve B_late_stance sc _late_stance indicator (i.e., the cost matrix for the end of the support period); calculate the C of curve A_swing and curve B_swing sc _swing indicator (i.e. the cost matrix for the swing period).

[0150] In some embodiments, the cost matrix between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase is calculated in step 142 to obtain the cost matrix of each gait phase, including:

[0151] Step 1421, calculate the reference distance matrix and reference angle matrix of the reference sub-hip and knee joint angle cycle diagram of each gait phase, and calculate the reference histogram matrix of the reference sub-hip and knee joint angle cycle diagram of each gait phase based on the reference distance matrix and the reference angle matrix.

[0152] Optionally, reference histogram matrices of reference sub-hip and knee angle cycle diagrams (ie, A_early_stance, A_mid_stance, A_late_stance, and A_swing) of the early stance, mid stance, late stance, and swing phases are calculated, respectively.

[0153] Step 1422, calculate the target distance matrix and target angle matrix of the target sub-hip and knee joint angle cycle diagram for each gait phase, and based on the target distance matrix and the target angle matrix, calculate the target histogram matrix of the target sub-hip and knee joint angle cycle diagram for each gait phase.

[0154] Optionally, target histogram matrices of target sub-hip and knee angle cycle diagrams (ie, B_early_stance, B_mid_stance, B_late_stance, and B_swing) are calculated for the early stance, mid stance, late stance, and swing phases, respectively.

[0155] Step 1423, based on the target histogram matrix and the reference histogram matrix, calculate the cost matrix between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase.

[0156] Step 143, based on the shortest matching path of each gait phase and the cost matrix of each gait phase, calculate the shape deviation evaluation value between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase, and obtain the shape deviation evaluation value of each gait phase.

[0157] Optionally, the shape deviation evaluation values ​​in the early support period, the middle support period, the end support period, and the swing period are calculated, and the expressions are as follows:

[0158] ;

[0159] ;

[0160] ;

[0161] ;

[0162] in, Indicates the shape deviation evaluation value of the support in the early stage, Indicates the shape deviation evaluation value in the middle stage of support, represents the shape deviation evaluation value at the end of support, Indicates the shape deviation evaluation value of the swing period.

[0163] Step 150: Evaluate the patient's hip and knee coordination based on the global shape deviation evaluation value and the shape deviation evaluation value of each gait phase to obtain an evaluation result.

[0164] Optionally, a global evaluation is performed on the patient's hip and knee joint coordination according to the global shape deviation evaluation value of each gait cycle to obtain a global evaluation result.

[0165] Optionally, a fine-grained assessment is performed on the patient's hip and knee joint coordination based on the shape deviation assessment value of each gait phase of each gait cycle to obtain a fine-grained assessment result.

[0166] It can be understood that by evaluating the patient's hip and knee coordination based on the global shape deviation evaluation value and the shape deviation evaluation value of each gait phase, the comprehensiveness and refinement of the evaluation are improved, the patient's specific problems in each gait phase can be discovered, and it helps to improve the accuracy of disease diagnosis.

[0167] It should be noted that the fine-grained hip-knee coordination assessment method provided in the embodiment of the present invention can be extended to other joints, such as knee-ankle joints, hip-ankle joints, and shoulder-elbow joints. The patients involved in the embodiment of the present invention include not only hemiplegic patients, but also Parkinson's patients, Alzheimer's patients, etc.

[0168] The fine-grained hip-knee joint coordination assessment device provided by an embodiment of the present invention is described below. The fine-grained hip-knee joint coordination assessment device described below and the fine-grained hip-knee joint coordination assessment method described above can be referenced to each other.

[0169] Figure 4 A schematic diagram of the structure of a fine-grained hip-knee joint coordination assessment device provided by an embodiment of the present invention is shown in FIG. Figure 4 As shown, the fine-grained hip-knee joint coordination assessment device 400 includes:

[0170] An acquisition unit 410 is used to determine a reference hip-knee joint angle cycle diagram and a reference plantar pressure curve diagram of a healthy person in each gait cycle, and to acquire a target hip-knee joint angle cycle diagram and a target plantar pressure curve diagram of a patient in each gait cycle;

[0171] A first calculation unit 420 is used to calculate a shape deviation evaluation value between a target hip and knee joint angle cycle diagram and a reference hip and knee joint angle cycle diagram based on a dynamic time planning-shape context algorithm to obtain a global shape deviation evaluation value;

[0172] A division unit 430 is used to divide the reference hip-knee joint angle cycle diagram into a plurality of reference sub-hip-knee joint angle cycle diagrams of a plurality of gait phases based on the reference plantar pressure curve diagram, and to divide the target hip-knee joint angle cycle diagram into a plurality of target sub-hip-knee joint angle cycle diagrams of a plurality of gait phases based on the target plantar pressure curve diagram;

[0173] A second calculation unit 440 is used to calculate a shape deviation evaluation value between a target sub-hip and knee joint angle cycle diagram and a corresponding reference sub-hip and knee joint angle cycle diagram for each gait phase based on a dynamic time planning-shape context algorithm to obtain a shape deviation evaluation value for each gait phase;

[0174] The evaluation unit 450 is used to evaluate the patient's hip and knee coordination according to the global shape deviation evaluation value and the shape deviation evaluation value of each gait phase to obtain an evaluation result.

[0175] Optionally, the multiple gait phases include early stance, mid-stance, end-stance and swing phase.

[0176] Optionally, based on the dynamic time planning-shape context algorithm, a shape deviation evaluation value between a target sub-hip and knee joint angle cycle diagram and a corresponding reference sub-hip and knee joint angle cycle diagram of each gait phase is calculated to obtain a shape deviation evaluation value of each gait phase, including:

[0177] Based on the dynamic time planning algorithm, the shortest matching path between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase is calculated to obtain the shortest matching path of each gait phase, and the shortest matching path of each gait phase is visualized;

[0178] Based on the dynamic time planning-shape context algorithm, the cost matrix between the target sub-hip and knee joint angle cycle graph of each gait phase and the reference sub-hip and knee joint angle cycle graph of each gait phase is calculated to obtain the cost matrix of each gait phase;

[0179] According to the shortest matching path of each gait phase and the cost matrix of each gait phase, the shape deviation evaluation value between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase is calculated to obtain the shape deviation evaluation value of each gait phase.

[0180] Optionally, the shortest matching path between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase is calculated to obtain the shortest matching path of each gait phase, including:

[0181] Calculate the distance matrix between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase to obtain the distance matrix of each gait phase;

[0182] Based on the distance matrix of each gait phase, the cumulative cost matrix between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase is calculated to obtain the cumulative cost matrix of each gait phase;

[0183] Determine the boundary conditions, and based on the cumulative cost matrix and boundary conditions of each gait phase, calculate the shortest matching path between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase to obtain the shortest matching path of each gait phase.

[0184] Optionally, a cost matrix between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase is calculated to obtain a cost matrix for each gait phase, including:

[0185] Calculate the reference distance matrix and reference angle matrix of the reference sub-hip and knee joint angle cycle diagram of each gait phase, and calculate the reference histogram matrix of the reference sub-hip and knee joint angle cycle diagram of each gait phase based on the reference distance matrix and the reference angle matrix;

[0186] Calculate the target distance matrix and target angle matrix of the target sub-hip and knee joint angle cycle diagram of each gait phase, and calculate the target histogram matrix of the target sub-hip and knee joint angle cycle diagram of each gait phase based on the target distance matrix and the target angle matrix;

[0187] Based on the target histogram matrix and the reference histogram matrix, the cost matrix between the target sub-hip and knee joint angle cyclic graph of each gait phase and the reference sub-hip and knee joint angle cyclic graph of each gait phase is calculated.

[0188] Optionally, based on the dynamic time planning-shape context algorithm, a shape deviation evaluation value between the target hip and knee joint angle cycle graph and the reference hip and knee joint angle cycle graph is calculated to obtain a global shape deviation evaluation value, including:

[0189] Based on the dynamic time planning algorithm, the shortest matching path between the target hip and knee joint angle cycle diagram and the reference hip and knee joint angle cycle diagram is calculated to obtain the global shortest matching path, and the global shortest matching path is visualized;

[0190] Based on the dynamic time planning-shape context algorithm, the cost matrix between the target hip and knee joint angle cycle graph and the reference hip and knee joint angle cycle graph is calculated to obtain the global cost matrix;

[0191] According to the global shortest matching path and the global cost matrix, the shape deviation evaluation value between the target hip and knee joint angle cycle graph and the reference hip and knee joint angle cycle graph is calculated to obtain the global shape deviation evaluation value.

[0192] Optionally, determining a reference hip and knee joint angle cycle diagram and a reference plantar pressure curve diagram of a healthy person in each gait cycle includes:

[0193] Acquire a first lower limb kinematics video and first plantar pressure data of a healthy person in each gait cycle, and obtain first hip joint angle data and first knee joint angle data based on the first lower limb kinematics video;

[0194] Determine a reference hip and knee joint angle cycle diagram according to the first hip joint angle data and the first knee joint angle data;

[0195] A reference plantar pressure curve graph is determined according to the first plantar pressure data.

[0196] Optionally, a target hip and knee joint angle cycle diagram and a target plantar pressure curve diagram of the patient in each gait cycle are obtained, including:

[0197] Acquire a second lower limb kinematics video and second plantar pressure data of the patient in each gait cycle, and obtain second hip joint angle data and second knee joint angle data based on the second lower limb kinematics video;

[0198] generating a target hip and knee joint angle cycle diagram based on the second hip joint angle data and the second knee joint angle data;

[0199] A target plantar pressure curve graph is generated based on the second plantar pressure data.

[0200] It should be noted here that the fine-grained hip and knee joint coordination assessment device provided by the embodiment of the present invention can implement all the method steps implemented by the above-mentioned fine-grained hip and knee joint coordination assessment method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0201] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.

[0202] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0203] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A fine-grained hip-knee joint coordination assessment method, characterized in that: include: Determine a reference hip-knee joint angle cycle diagram and a reference plantar pressure curve diagram of a healthy person in each gait cycle, and obtain a target hip-knee joint angle cycle diagram and a target plantar pressure curve diagram of a patient in each gait cycle; Based on the dynamic time planning-shape context algorithm, a shape deviation evaluation value between the target hip and knee joint angle cycle graph and the reference hip and knee joint angle cycle graph is calculated to obtain a global shape deviation evaluation value; Based on the reference plantar pressure curve graph, dividing the reference hip-knee joint angle cycle graph into a plurality of reference sub-hip-knee joint angle cycle graphs of a plurality of gait phases; based on the target plantar pressure curve graph, dividing the target hip-knee joint angle cycle graph into a plurality of target sub-hip-knee joint angle cycle graphs of a plurality of gait phases; Based on the dynamic time planning-shape context algorithm, the shape deviation evaluation value between the target sub-hip and knee joint angle cycle diagram and the corresponding reference sub-hip and knee joint angle cycle diagram of each gait phase is calculated to obtain the shape deviation evaluation value of each gait phase; The patient's hip and knee joint coordination is evaluated based on the global shape deviation evaluation value and the shape deviation evaluation value of each gait phase to obtain an evaluation result.

2. The fine-grained hip-knee joint coordination assessment method according to claim 1, characterized in that: The multiple gait phases include early stance, mid-stance, end-stance and swing phase.

3. The fine-grained hip-knee joint coordination assessment method according to claim 1, characterized in that: The shape deviation evaluation value between the target sub-hip and knee joint angle cycle diagram and the corresponding reference sub-hip and knee joint angle cycle diagram of each gait phase is calculated based on the dynamic time planning-shape context algorithm to obtain the shape deviation evaluation value of each gait phase, including: Based on the dynamic time planning algorithm, the shortest matching path between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase is calculated to obtain the shortest matching path of each gait phase, and the shortest matching path of each gait phase is visualized; Based on the dynamic time planning-shape context algorithm, a cost matrix between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase is calculated to obtain the cost matrix of each gait phase; According to the shortest matching path of each gait phase and the cost matrix of each gait phase, the shape deviation evaluation value between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase is calculated to obtain the shape deviation evaluation value of each gait phase.

4. The fine-grained hip-knee joint coordination assessment method according to claim 3, characterized in that: The shortest matching path between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase is calculated to obtain the shortest matching path of each gait phase, including: Calculate the distance matrix between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase to obtain the distance matrix of each gait phase; Based on the distance matrix of each gait phase, a cumulative cost matrix between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase is calculated to obtain a cumulative cost matrix of each gait phase; Determine the boundary conditions, and based on the cumulative cost matrix of each gait phase and the boundary conditions, calculate the shortest matching path between the target sub-hip and knee joint angle cycle graph of each gait phase and the reference sub-hip and knee joint angle cycle graph of each gait phase to obtain the shortest matching path of each gait phase.

5. The fine-grained hip-knee joint coordination assessment method according to claim 3, characterized in that: The step of calculating the cost matrix between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase to obtain the cost matrix of each gait phase includes: Calculate a reference distance matrix and a reference angle matrix of the reference sub-hip and knee joint angle cycle diagram of each gait phase, and calculate a reference histogram matrix of the reference sub-hip and knee joint angle cycle diagram of each gait phase based on the reference distance matrix and the reference angle matrix; Calculate the target distance matrix and target angle matrix of the target sub-hip and knee joint angle cycle diagram of each gait phase, and calculate the target histogram matrix of the target sub-hip and knee joint angle cycle diagram of each gait phase based on the target distance matrix and target angle matrix; Based on the target histogram matrix and the reference histogram matrix, a cost matrix between the target sub-hip and knee joint angle cycle diagram of each gait phase and the reference sub-hip and knee joint angle cycle diagram of each gait phase is calculated.

6. The fine-grained hip-knee joint coordination assessment method according to claim 1, characterized in that: The method of calculating the shape deviation evaluation value between the target hip-knee joint angle cycle graph and the reference hip-knee joint angle cycle graph based on the dynamic time planning-shape context algorithm to obtain a global shape deviation evaluation value includes: Based on a dynamic time planning algorithm, the shortest matching path between the target hip-knee joint angle cycle diagram and the reference hip-knee joint angle cycle diagram is calculated to obtain a global shortest matching path, and the global shortest matching path is visualized; Based on the dynamic time planning-shape context algorithm, a cost matrix between the target hip and knee joint angle cycle graph and the reference hip and knee joint angle cycle graph is calculated to obtain a global cost matrix; According to the global shortest matching path and the global cost matrix, a shape deviation evaluation value between the target hip-knee joint angle cycle graph and the reference hip-knee joint angle cycle graph is calculated to obtain the global shape deviation evaluation value.

7. The fine-grained hip-knee joint coordination assessment method according to claim 1, characterized in that: The method of determining a reference hip and knee joint angle cycle diagram and a reference plantar pressure curve diagram of a healthy person in each gait cycle includes: Acquire a first lower limb kinematics video and first plantar pressure data of a healthy person in each gait cycle, and obtain first hip joint angle data and first knee joint angle data based on the first lower limb kinematics video; Determining the reference hip and knee joint angle cycle diagram according to the first hip joint angle data and the first knee joint angle data; The reference plantar pressure curve graph is determined according to the first plantar pressure data.

8. The fine-grained hip-knee joint coordination assessment method according to claim 1, characterized in that: The method of obtaining a target hip and knee joint angle cycle diagram and a target plantar pressure curve diagram of the patient in each gait cycle includes: Acquire a second lower limb kinematics video and second plantar pressure data of the patient in each gait cycle, and obtain second hip joint angle data and second knee joint angle data based on the second lower limb kinematics video; generating the target hip and knee joint angle cycle diagram based on the second hip joint angle data and the second knee joint angle data; The target plantar pressure curve graph is generated based on the second plantar pressure data.

9. A fine-grained hip-knee joint coordination assessment device, characterized in that: include: An acquisition unit is used to determine a reference hip and knee joint angle cycle diagram and a reference plantar pressure curve diagram of a healthy person in each gait cycle, and to acquire a target hip and knee joint angle cycle diagram and a target plantar pressure curve diagram of a patient in each gait cycle; A first calculation unit is used to calculate a shape deviation evaluation value between the target hip and knee joint angle cycle graph and the reference hip and knee joint angle cycle graph based on a dynamic time planning-shape context algorithm to obtain a global shape deviation evaluation value; a dividing unit, for dividing the reference hip-knee joint angle cycle diagram into a plurality of reference sub-hip-knee joint angle cycle diagrams of a plurality of gait phases based on the reference plantar pressure curve diagram, and for dividing the target hip-knee joint angle cycle diagram into a plurality of target sub-hip-knee joint angle cycle diagrams of a plurality of gait phases based on the target plantar pressure curve diagram; A second calculation unit is used to calculate a shape deviation evaluation value between a target sub-hip and knee joint angle cycle diagram and a corresponding reference sub-hip and knee joint angle cycle diagram for each gait phase based on a dynamic time planning-shape context algorithm to obtain a shape deviation evaluation value for each gait phase; The evaluation unit is used to evaluate the patient's hip and knee joint coordination according to the global shape deviation evaluation value and the shape deviation evaluation value of each gait phase to obtain an evaluation result.

10. A fine-grained hip-knee joint coordination assessment system, characterized in that: include: A binocular near-infrared camera, an RGB camera, a video capture module, a plantar pressure sensor, and a fine-grained hip-knee coordination assessment device as described in claim 9; The binocular near-infrared camera is used to record black-and-white video of the movement of human lower limbs; The RGB camera is used to visualize and record color video of human lower limb movements; The video capture module is used to receive the black-and-white video of the human lower limb movement and the color video of the human lower limb movement to generate a lower limb kinematics video, and send the lower limb kinematics video to the fine-grained hip and knee coordination assessment device; The plantar pressure sensor is used to collect plantar pressure data of a human body and send the plantar pressure data to the fine-grained hip-knee joint coordination assessment device.

Images