Computer vision-based limb movement disorder recognition and active movement assistance control method

Abstract

The application provides a computer vision-based limb movement disorder identification and active movement assistance control method, and relates to the technical field of movement rehabilitation engineering.The application obtains a movement image sequence of upper limbs and / or lower limbs of a patient, extracts multi-joint three-dimensional coordinates to form spatial position data, and calculates joint angles and angular velocities to obtain joint movement state data.Combining force and moment support evidence, joint angle deviation, angular velocity anomaly and compensation behavior are identified, movement disorder identification results containing intention intensity and compensation index are generated, target assisted joints and assisted torque outputs are determined accordingly, and active movement assistance control is implemented in the form of joint driving assistance, torque compensation, trajectory amplification or lateral force compensation and the like.The application can achieve fine identification and adaptive assistance of movement disorders without additional wearable equipment, and improves the accuracy and safety of rehabilitation training.

Description

Technical Field

[0001] This invention relates to the field of sports rehabilitation engineering technology, and in particular to a computer vision-based method for identifying limb movement disorders and actively assisting in movement control. Background Technology

[0002] With an aging society and the increasing incidence of diseases such as stroke and trauma, the number of patients with upper and lower limb movement disorders continues to rise. Traditional rehabilitation training methods mainly rely on manual stretching and passive movements by therapists. The intensity and rhythm of training are greatly influenced by human experience, and the training process is difficult to quantify precisely and record over a long period. In recent years, intelligent rehabilitation devices such as rehabilitation robots and exoskeletons have emerged, which can achieve high repeatability and high precision training control to a certain extent. However, most systems currently rely mainly on joint encoders, position / force sensors, or electromyographic signals to determine the patient's movement status. They are unable to comprehensively perceive the postural changes of multiple joints such as the shoulder, elbow, wrist, hip, knee, and ankle in the spatial dimension, and especially cannot distinguish between the patient's true motor ability and compensatory movements.

[0003] With the development of computer vision and kinematic modeling technologies, the identification and analysis of three-dimensional motion of multiple joints in the human body using visual sensing technology has become an important development direction in the rehabilitation field. In rehabilitation training scenarios, how to acquire the spatial coordinates and joint angles of key joints in the patient's upper and lower limbs in real time without adding extra mechanical burden, combine this with the desired motion trajectory and real-time motion performance, identify movement disorders and compensatory behaviors, and adaptively adjust the output of the rehabilitation robot accordingly, is a crucial technical path to improve the safety and effectiveness of training. Therefore, an integrated approach combining visual perception, movement disorder recognition, and active motion-assisted control has become an important development trend for rehabilitation robots and exoskeleton control systems.

[0004] Existing rehabilitation systems that rely on mechanical sensors or electromyography signals have difficulty in timely identifying upper limb abnormalities such as shoulder shrugging, forward or lateral bending of the trunk, limited or abnormal flexion and extension of the elbow, and abnormal dorsiflexion or deviation from the target direction of the wrist. They also have difficulty in timely identifying gait abnormalities such as excessive swinging or raising of the hip joint, insufficient flexion and extension of the knee or hyperextension of the knee, and foot drop or inversion and eversion of the ankle. As a result, it is difficult to accurately determine whether the patient has fallen into a movement disorder or whether there is obvious compensatory behavior, which can easily lead to improper assistance or even sports injury. Summary of the Invention

[0005] To overcome the shortcomings of existing technologies, the purpose of this invention is to provide a computer vision-based method for identifying limb movement disorders and active motion assistance control. By acquiring multi-joint three-dimensional motion information through computer vision and combining it with force and torque support evidence, the method can achieve precise identification of movement disorders and compensatory behaviors. It outputs intention intensity and compensation index to drive adaptive, multi-strategy active motion assistance control, thereby significantly improving the accuracy, safety and effectiveness of rehabilitation training without increasing the burden of wearing additional clothing.

[0006] To achieve the above objectives, the present invention provides the following solution: A computer vision-based method for limb movement disorder recognition and active movement assistance control includes: Acquire motion image sequences of the patient's upper and / or lower limbs, and extract the three-dimensional coordinates of the trunk, shoulder joint, elbow joint, wrist joint, hip joint, knee joint, ankle joint and toe points to form spatial position data of multiple joints; Based on the spatial location data, construct multi-segment vectors of the limbs and calculate the vector angles to obtain joint angles and joint angular velocities, thus forming joint motion state data; Based on the joint motion state data and combined with force and torque support evidence, the joint angle deviation, angular velocity abnormality and torque abnormality are judged, the corresponding movement disorder type is identified, and it is determined whether there is trunk compensation or joint compensation behavior. The intention intensity and compensation index are output to form the movement disorder identification result. Based on the movement disorder identification results, the direction and magnitude of the target auxiliary joint and the auxiliary torque are determined, movement assistance control commands are generated, and active movement assistance control is implemented through at least one of the following methods: joint drive assistance, torque compensation, trajectory amplification, mechanical limit or damping, and lateral force compensation, to guide the patient to complete preset rehabilitation training movements.

[0007] Preferably, constructing multi-segment vectors of the limbs based on the spatial location data and calculating the angle between the vectors includes: Using the three-dimensional coordinates of the shoulder joint, elbow joint, wrist joint and torso point in the spatial location data, construct the upper arm vector from the shoulder joint to the elbow joint, the forearm vector from the elbow joint to the wrist joint and the torso vector from the torso point to the shoulder joint. Calculate the angle between the upper arm vector and the torso vector, and the angle between the upper arm vector and the forearm vector, to obtain the shoulder joint angle and the elbow joint angle; Based on the changes in the shoulder joint angle and elbow joint angle over time, the shoulder joint angular velocity and elbow joint angular velocity are obtained respectively, so that the joint motion state data includes at least the shoulder joint angle, shoulder joint angular velocity, elbow joint angle, and elbow joint angular velocity.

[0008] Preferably, constructing multi-segment vectors of the limbs based on the spatial location data and calculating the angle between the vectors further includes: Using the three-dimensional coordinates of the hip joint, knee joint, ankle joint, and toe points in the spatial location data, construct the thigh vector from the hip joint to the knee joint, the lower leg vector from the knee joint to the ankle joint, and the foot segment vector from the ankle joint to the toe points; Calculate the angle between the thigh vector and the calf vector, and the angle between the calf vector and the foot segment vector to obtain the knee joint angle and the ankle joint angle. Based on the changes of the knee joint angle and the ankle joint angle over time, obtain the knee joint angular velocity and the ankle joint angular velocity, respectively. The hip joint angle and hip joint angular velocity are determined based on the positional relationship of the hip joint in the spatial position data, so that the joint motion state data includes at least the hip joint angle, hip joint angular velocity, knee joint angle, knee joint angular velocity, ankle joint angle, and ankle joint angular velocity.

[0009] Preferably, based on the joint motion state data and combined with force and torque support evidence, joint angle deviation, angular velocity abnormality, and torque abnormality are determined to identify the corresponding type of movement disorder, including: In the joint motion state data, when the shoulder joint angle and shoulder joint angular velocity are inconsistent with the preset shoulder joint motion range and change pattern, and the displacement of the trunk point in the spatial position data determines that the trunk exceeds the preset range in the vertical or forward and backward directions, it is determined that there is a compensatory behavior of the trunk such as shrugging or the trunk leaning forward or bending to the side. In the joint motion state data, when the elbow joint angle does not reach the expected range within a preset time, or the elbow joint angle change trend is opposite to the preset target direction, and the elbow joint angular velocity shows a significant decrease or sudden change, the movement disorder of elbow joint flexion and extension or abnormal bending is determined by combining the force and torque support evidence. In the joint motion state data, when the joint angle of the wrist joint relative to the forearm continuously exceeds the preset normal range, or when the wrist movement trajectory obtained according to the spatial position data deviates from the target direction by more than a preset threshold, it is determined that there is a movement disorder of abnormal dorsiflexion, palmar flexion or deviation of the wrist joint.

[0010] Preferably, based on the joint motion state data and combined with force and torque support evidence, determining joint angle deviation, angular velocity abnormality, and torque abnormality, and identifying the corresponding type of movement disorder, further includes: During the gait swing phase, if the maximum flexion value of the knee joint angle in the joint motion state data is lower than the preset flexion threshold, it is determined that there is insufficient knee flexion and extension. During the gait support phase, if the knee joint angle in the joint motion state data exceeds the preset upper limit of extension and shows a backward bending trend, and the force and torque support evidence related to the knee joint shows abnormal force, it is determined that there is a knee retraction. When the knee joint angular velocity in the joint motion state data shows frequent pauses, abrupt changes, or irregular high-frequency fluctuations within a continuous gait cycle, it is determined that there is a movement disorder involving knee joint locking.

[0011] Preferably, based on the joint motion state data and combined with force and torque support evidence, determining joint angle deviation, angular velocity abnormality, and torque abnormality, and identifying the corresponding type of movement disorder, further includes: During the gait swing phase, if the ankle joint angle in the joint motion state data does not reach the preset dorsiflexion angle, and the foot segment is determined to be in a toe-down posture based on the spatial position data, foot drop is determined to exist. During standing or gait progression, if the ankle joint angle in the plantar flexion direction in the joint motion state data continuously exceeds a preset range, and the force and torque support evidence related to the ankle joint indicates instability in weight-bearing, it is determined that there is excessive plantar flexion of the ankle joint. When the foot segment is determined to deviate continuously from the direction of inversion or eversion relative to the ground normal direction based on the spatial position data and exceeds a preset range, it is determined that there is a movement disorder of ankle inversion or eversion.

[0012] Preferably, based on the motion disorder identification results, the target assist joint and the direction and magnitude of the assist torque are determined, motion assist control commands are generated, and active motion assist control is implemented through at least one of the following methods: joint drive assistance, torque compensation, trajectory amplification, mechanical limiting or damping, and lateral force compensation, to guide the patient to complete preset rehabilitation training movements, including: When the movement disorder identification results indicate the presence of shoulder shrugging or trunk compensation behavior, reduce the auxiliary force along the trunk lifting or forward leaning direction, and adjust the auxiliary force to target the elbow joint as the auxiliary joint and apply auxiliary torque along the elbow joint flexion and extension direction; When the movement disorder identification result indicates that there is limited flexion and extension or abnormal bending of the elbow joint, the elbow joint is set as the target auxiliary joint. The direction and magnitude of the auxiliary torque are determined according to the deviation between the elbow joint angle and the elbow joint angular velocity and the preset target, so that the elbow joint movement approaches the preset target trajectory. When the movement disorder identification result indicates the presence of abnormal dorsiflexion or palmar flexion of the wrist joint, the wrist joint is set as the target auxiliary joint, and an auxiliary torque is applied at the end-effector position to counteract the abnormal dorsiflexion or palmar flexion, so that the wrist joint is kept in a near-neutral position.

[0013] Preferably, based on the motion disorder identification results, the target assist joint and the direction and magnitude of the assist torque are determined, motion assist control commands are generated, and active motion assist control is implemented through at least one of the following methods: joint drive assistance, torque compensation, trajectory amplification, mechanical limiting or damping, and lateral force compensation, to guide the patient to complete preset rehabilitation training movements. The method also includes: When the movement disorder identification result indicates that there is insufficient knee flexion and extension, the knee joint is set as the target auxiliary joint, and an auxiliary torque is applied along the knee flexion direction during the gait swing phase, and the knee flexion angle is amplified within a preset range. When the movement disorder identification result indicates the presence of hyperextension of the knee, the knee joint is set as the target auxiliary joint, and a limiting auxiliary torque is applied along the knee flexion direction during the gait support phase to suppress hyperextension and hyperbending of the knee joint. When the movement disorder identification results indicate the presence of knee joint slack, rhythmic, small-amplitude flexion-extension auxiliary torques are applied to the knee joint during continuous gait cycles to improve the continuity and smoothness of knee joint angle and knee joint angular velocity.

[0014] Preferably, based on the motion disorder identification results, the target assist joint and the direction and magnitude of the assist torque are determined, motion assist control commands are generated, and active motion assist control is implemented through at least one of the following methods: joint drive assistance, torque compensation, trajectory amplification, mechanical limiting or damping, and lateral force compensation, to guide the patient to complete preset rehabilitation training movements. The method also includes: When the movement disorder identification result indicates the presence of foot drop, the ankle joint is set as the target auxiliary joint, and an auxiliary torque is applied along the dorsiflexion direction of the ankle joint during the gait swing phase to lift the foot and reduce the risk of dragging. When the movement disorder identification result indicates that there is excessive plantar flexion of the ankle joint, the ankle joint is set as the target auxiliary joint, an upper limit of the auxiliary torque or equivalent damping is set in the plantar flexion direction, and support is provided in the dorsiflexion direction of the ankle joint when weight-bearing is required; When the movement disorder identification result indicates the presence of ankle inversion or eversion, the ankle joint is designated as the target auxiliary joint, and a lateral auxiliary force or limiting auxiliary torque is applied in the inversion or eversion direction to maintain balanced contact of the sole of the foot.

[0015] Preferably, it further includes: During multiple rehabilitation training sessions, the intent intensity, compensation index, and corresponding motor assist control commands in the motor impairment recognition results obtained from each training session are recorded. In subsequent training sessions, the selection of the target assist joint and the direction and magnitude of the assist torque are adaptively adjusted based on the recorded content to optimize the active motor assist control effect.

[0016] The present invention discloses the following technical effects: This invention acquires motion image sequences of a patient's upper and / or lower limbs, extracts three-dimensional coordinates of multiple joints to form multi-joint spatial position data, and then calculates joint angles and angular velocities through vector angle calculations to form joint motion state data, achieving a three-dimensional, continuous, and quantitative representation of the limb movement process. Compared to existing solutions that mainly rely on empirical observation or single sensor signals, this invention, without increasing the burden of wearing protective gear, can simultaneously cover the trunk, shoulder, elbow, wrist, hip, knee, ankle, and toe points, significantly improving the spatial resolution of complex upper limb movements and gait chains. This provides a complete and reliable data foundation for subsequent movement disorder identification, overcoming the problems of "incomplete visualization, unclear measurement, and inability to remember" in existing technologies.

[0017] This invention, based on joint motion data, introduces force and torque support evidence to jointly assess joint angle deviations, abnormal angular velocities, and abnormal torques. It further identifies trunk or joint compensatory behaviors, thus distinguishing between "patient's actual inability to perform tasks" and "completing tasks through compensatory movements such as shoulder shrugging, forward leaning, and hip swaying." Compared to existing schemes that rely solely on joint encoders, end-effector displacement, or single electromyographic signals to determine motion status, the multidimensional evidence chain constructed in this invention can detect abnormal patterns such as shoulder shrugging, trunk forward leaning, knee hyperextension, foot drop, and inversion / eversion earlier and more accurately, effectively compensating for the shortcomings of traditional systems in insufficient identification of compensatory behaviors and coarse classification of movement disorders.

[0018] This invention outputs intention intensity and compensation index based on joint motion state data and force and torque support evidence to form a movement disorder identification result, which drives subsequent auxiliary decisions and establishes a closed-loop link from "passive monitoring" to "quantitative assessment" and then to adaptive assistance. Compared with existing rehabilitation equipment that can only output auxiliary force according to fixed programs or simple threshold rules, this invention reflects the patient's active intention through intention intensity and characterizes the degree of compensation through compensation index. This allows the auxiliary force, intervention timing, and intervention joints to be dynamically adjusted according to the patient's state, thereby achieving individualized and phased optimization of rehabilitation programs and avoiding the two extremes of "too much assistance" inhibiting active participation or "too little assistance" leading to training failure.

[0019] After obtaining the movement disorder identification results, this invention generates movement-assisted control commands that include the target auxiliary joint and the direction and magnitude of the auxiliary torque, targeting different joints and different disorder types. It then implements active movement-assisted control through at least one of the following methods: joint drive assistance, torque compensation, trajectory amplification, mechanical limiting or damping, and lateral force compensation. Compared with existing solutions that only provide single-force assistance or simply limit the range of motion of joints, this invention can execute differentiated and refined control strategies for key joints such as the shoulder, elbow, wrist, hip, knee, and ankle. This enhances insufficient movements such as flexion and dorsiflexion while suppressing dangerous postures such as hyperextension, excessive plantar flexion, and abnormal inversion / exversion. It improves training effectiveness while reducing the risk of secondary injury, significantly enhancing the safety and effectiveness of rehabilitation training. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart of a method provided in an embodiment of the present invention. Detailed Implementation

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

[0023] The purpose of this invention is to provide a method that, by constructing a closed loop of "three-dimensional joint motion perception - obstacle and compensation identification - precise auxiliary control", accurately judges the patient's actual motor ability and provides targeted assistance, thereby significantly improving the intelligence, adaptability and safety of rehabilitation training.

[0024] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0025] Figure 1 The method flowchart provided in the embodiments of the present invention is as follows: Figure 1 As shown, this invention provides a computer vision-based method for limb movement disorder recognition and active movement assistance control, comprising: Step 100: Obtain motion image sequences of the patient's upper and / or lower limbs, and extract the three-dimensional coordinates of the trunk point, shoulder joint, elbow joint, wrist joint, hip joint, knee joint, ankle joint and toe point to form spatial position data of multiple joints; Step 200: Construct multi-segment vectors of the limbs based on spatial location data and calculate the angle between the vectors to obtain joint angles and joint angular velocities, thus forming joint motion state data; Step 300: Based on the joint motion state data and combined with force and torque support evidence, determine the joint angle deviation, angular velocity abnormality and torque abnormality, identify the corresponding movement disorder type, determine whether there is trunk compensation or joint compensation behavior, output the intention intensity and compensation index, and form the movement disorder identification result. Step 400: Based on the motion disorder identification results, determine the target assist joint and the direction and magnitude of the assist torque, generate motion assist control commands, and implement active motion assist control through at least one of the following methods: joint drive assistance, torque compensation, trajectory amplification, mechanical limit or damping, and lateral force compensation, to guide the patient to complete the preset rehabilitation training movements.

[0026] This embodiment provides a computer vision-based method for identifying and actively controlling limb movement disorders, applied to upper and lower limb active movement rehabilitation training scenarios. When patients are unable to complete expected movements due to motor impairment or insufficient muscle strength, during active upper limb movements, abnormal shoulder shrugging, internal rotation, or significant trunk compensation are common; elbow flexion and extension are limited or abnormally bent; and wrists exhibit abnormal dorsiflexion, palmar flexion, or distal deviation from the target direction. During active lower limb movements, when gait is limited, excessive hip swinging or elevation, excessive forward or lateral trunk tilting, insufficient knee flexion and extension, hyperextension, or angular velocity stagnation are common; and ankles exhibit foot drop, excessive plantar flexion, or inversion / eversion. This embodiment aims to maximize the patient's active participation while ensuring training safety by unifying visual perception, identification, and control of the aforementioned abnormal joint manifestations.

[0027] In the overall process of this embodiment, image sequences of the patient's upper and / or lower limbs during active movement are first acquired using computer vision. Image processing and pose estimation algorithms are then used to extract the three-dimensional coordinates of the trunk, shoulder, elbow, wrist, hip, knee, ankle, and toe points in the world coordinate system, constructing temporal data containing the spatial positions of multiple joints. Subsequently, the joint angles and angular velocities of each joint are calculated based on the temporal changes in joint positions, forming joint motion state information describing the joint movement process. Combining the initial position, target position, and a preset joint kinematic model, the expected angle change trend of each joint when completing a training task is given, and compared with the real-time observed joint angles and angular velocities to determine the patient's current movement intention and whether there is a movement disorder. Depending on the type and severity of the disorder, the auxiliary output of the rehabilitation robot or exoskeleton is further adjusted in this embodiment, so that the auxiliary intensity and the intervention joints change in real time with the patient's state.

[0028] In terms of identifying abnormalities in active upper limb movements, this embodiment sets up a visual perception recognition process for analyzing specific patterns in key joints such as the shoulder, elbow, and wrist. When the relative position of the three-dimensional coordinates of the shoulder joint area and the trunk point shows abnormal shoulder elevation, excessive internal rotation angle, and a deviation of the trunk point from the normal range in the vertical or anteroposterior directions, it is considered as shrugging or trunk compensation. When the angle change of the elbow joint in the flexion and extension direction lags significantly behind the expected trajectory, or the direction of angle change is opposite to the expected direction, it is considered as limited flexion and extension or abnormal bending. When the angle of the wrist joint relative to the forearm deviates significantly from the natural neutral position, or the angle between the end handle and the target direction exceeds a preset threshold, it is considered as abnormal dorsiflexion, palmar flexion, or deviation from the target direction. Through the above identification, this embodiment can distinguish between different states of "insufficient actual ability" and "barely completing the movement through compensatory posture" among the joints of the upper limb.

[0029] To improve the stability of upper limb key feature extraction, this embodiment includes a preprocessing step in upper limb detection. First, in the patient's initial state of rest and no movement, the three-dimensional coordinates of the trunk, shoulder, elbow, and wrist joints in the world coordinate system are calibrated as a reference for subsequent calculations. During movement, the changes in the positions of these joints over time are estimated using differential or filtering methods to obtain smooth velocity and joint angular velocity curves. In geometric modeling, the upper arm vector is defined by the line connecting the shoulder and elbow joints, the forearm vector by the line connecting the elbow and wrist joints, and the trunk vector by the line connecting the trunk point and shoulder joints. The angles between these vectors are calculated to obtain the joint angles of the shoulder, elbow, and other joints. To avoid interference from abnormal noise, this embodiment sets an effective angle range for each joint angle. When the calculated angle exceeds this range, a flag indicating angle failure or unusability is output. This abnormal value is not directly used in subsequent obstacle recognition; instead, it is comprehensively judged in conjunction with temporal neighborhood information and other joint data.

[0030] Regarding the identification of abnormalities in active lower limb movements, this embodiment also uses a visual perception recognition process to jointly analyze the posture of the hip, knee, ankle, and trunk joints. When the swing amplitude of the hip joint is observed to significantly exceed the preset range during the gait cycle, or the relative trajectory with the pelvic point shows abnormal hip elevation, while the trunk point shows excessive forward or lateral tilt, it is considered an abnormality in the posture of the hip joint and trunk. When the flexion angle of the knee joint during the swing phase consistently fails to reach the expected range, or the knee joint angle during the stance phase exceeds the normal upper limit of extension, or even gradually bends backward, it is identified as insufficient knee flexion and extension or knee hyperextension. When the knee joint angular velocity sequence shows frequent sudden decreases, pauses, or high-frequency tremor patterns, it is identified as knee joint jamming. For the ankle joint, when the foot is consistently observed to be in a toe-down position with insufficient dorsiflexion during the swing phase, it is determined to be foot drop; when the plantar flexion angle exceeds the threshold for a long period during the weight-bearing or propulsion phase, it is determined to be excessive plantar flexion; when the foot is consistently deviated medially or laterally relative to the ground normal and exceeds the inversion or eversion threshold, it is determined to be ankle inversion or eversion abnormality.

[0031] In the preprocessing of lower limb detection, this embodiment first calibrates the three-dimensional coordinates of the hip, knee, ankle, toe, and pelvic points (as trunk points) in the world coordinate system under the initial state of the patient being at rest and without movement. This initial posture is used as the reference benchmark for subsequent gait analysis. During movement, the velocity and angular velocity of each joint position in the lower limb are estimated using differential or filtering methods to suppress noise interference. In terms of geometric modeling, the thigh (upper leg) vector is defined by the line connecting the hip and knee joints, the lower leg (lower leg) vector is defined by the line connecting the knee and ankle joints, and the foot segment vector is defined by the line connecting the ankle and toe points. The angles between these vectors are calculated to obtain the joint angles of the hip, knee, and ankle joints at each stage. A valid range is also set for these angles. When the angle exceeds the range, a flag indicating angle acquisition failure or unusability is output. This embodiment uses the aforementioned lower limb joint angles and corresponding angular velocities, along with three-dimensional position changes, as the basic data for the lower limb joint motion state, providing a reliable basis for gait obstacle identification and auxiliary decision-making.

[0032] In determining whether a patient needs assistance and the intensity of that assistance, this embodiment establishes a movement disorder assistance decision-making process and utilizes force sensors to acquire force and torque support evidence. Through comprehensive analysis of joint angles, joint angular velocities, and forces near the joints, it determines whether the patient encounters a movement disorder in the current action and assesses whether there is a significant compensatory pattern. Based on this information, this embodiment calculates a compensation index to quantify the degree of compensation and calculates the intensity of intent based on the patient's attempts to actively complete the action, thus forming a movement disorder identification result that includes both "intention intensity" and "presence of compensation." When this result indicates that the patient indeed has difficulty completing the action on their own and the risk of compensation is high, this embodiment activates or enhances the corresponding movement assistance output; when the intensity of intent is high but the compensation index is low, the level of assistance is appropriately reduced to encourage the patient to actively participate in training.

[0033] Regarding assistive measures for active upper limb movement, this embodiment designs targeted control strategies for abnormal manifestations of different joints. When abnormal shoulder shrugging, internal rotation, or trunk compensation is detected, this is considered an attempt by the patient to compensate for insufficient actual joint mobility by raising the shoulder or swinging the trunk. In this case, this embodiment no longer simply increases the assistive force in the shoulder direction, but instead transfers the shoulder-related assistive output to the flexion and extension direction of the elbow joint or the spatial movement direction of the forearm distal end, guiding the patient to complete the task with more reasonable elbow joint movement. When elbow flexion and extension are restricted or abnormal bending occurs, by comparing the angle between the patient's applied force direction and the desired target direction, the system automatically increases compliance along the target direction and reduces the resultant force deviating from the trajectory direction, allowing the elbow joint to complete flexion and extension movements near a safer and more natural trajectory. When abnormal dorsiflexion, palmar flexion, or distal deviation from the target occurs in the wrist joint, this embodiment applies a small corrective torque at the distal handle based on the visually detected abnormal wrist joint angle, gradually guiding the wrist joint to a near-natural neutral position, ensuring that the handle points more stably toward the target direction, thereby improving the accuracy and comfort of upper limb training.

[0034] Regarding assistive measures for lower limb movement disorders, this embodiment provides differentiated intervention methods for typical problems such as insufficient knee flexion and extension, hyperextension, and knee locking. When insufficient knee flexion angle is determined during the swing phase, this embodiment sets the knee joint as the key target for assistance, applying an auxiliary torque along the knee flexion direction during the swing phase, while simultaneously amplifying the knee flexion amplitude along a preset gait trajectory to guide the patient to complete a larger angle of flexion, thereby improving stride length and gait smoothness. When hyperextension is determined during the standing or weight-bearing phase, a restraining or inhibitory auxiliary torque is applied to the knee joint along the flexion direction to limit excessive knee extension and backward bending, avoiding long-term damage to the joint structure. When knee joint angular velocity is observed to lock or vibrate within a continuous gait cycle, this embodiment applies a rhythmic, small-amplitude flexion and extension auxiliary torque to the knee joint, playing a "rhythmic guidance" role, making knee joint angle changes more continuous and smooth, and improving overall gait coordination.

[0035] Regarding assistive measures for ankle joint movement disorders, this embodiment also provides specific control strategies for foot drop, excessive plantar flexion, and inversion / eversion. When insufficient dorsiflexion of the foot during the swing phase and toe pointing leading to foot drop are identified, this embodiment applies an auxiliary driving torque along the dorsiflexion direction of the ankle joint at this stage to lift the foot and reduce the risk of dragging and tripping. When excessive plantar flexion of the ankle joint is identified during standing or gait propulsion, mechanical limits or equivalent damping are set in the plantarflexion direction, and slight dorsiflexion support is provided during weight-bearing to maintain the ankle joint in a more stable weight-bearing posture. When abnormal inversion / eversion of the ankle joint is identified, this embodiment can combine a multi-degree-of-freedom ankle exoskeleton structure to provide support and restriction in the inversion or eversion direction, and apply lateral support force to the sole of the foot for lateral force compensation, making the contact between the sole of the foot and the ground more balanced, thereby improving the stability and safety during walking. Finally, by recording the results of movement disorder identification, compensation index, and auxiliary output during training and providing real-time feedback through a human-computer interaction interface, this embodiment can not only help patients adjust incorrect postures in a timely manner and avoid sports injuries caused by improper operation, but also provide a basis for optimizing subsequent rehabilitation programs and adjusting individualized parameters, thereby achieving closed-loop management of the entire rehabilitation training process.

[0036] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0037] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for limb movement disorder recognition and active movement assistance control based on computer vision, characterized in that, include: Acquire motion image sequences of the patient's upper and / or lower limbs, and extract the three-dimensional coordinates of the trunk, shoulder joint, elbow joint, wrist joint, hip joint, knee joint, ankle joint and toe points to form spatial position data of multiple joints; Based on the spatial location data, construct multi-segment vectors of the limbs and calculate the vector angles to obtain joint angles and joint angular velocities, thus forming joint motion state data; Based on the joint motion state data and combined with force and torque support evidence, the joint angle deviation, angular velocity abnormality and torque abnormality are judged, the corresponding movement disorder type is identified, and it is determined whether there is trunk compensation or joint compensation behavior. The intention intensity and compensation index are output to form the movement disorder identification result. Based on the movement disorder identification results, the direction and magnitude of the target assist joint and assist torque are determined, movement assist control commands are generated, and active movement assist control is implemented through at least one of the following methods: joint drive assistance, torque compensation, trajectory amplification, mechanical limit or damping, and lateral force compensation, to guide the patient to complete preset rehabilitation training movements. Based on the joint motion state data, and combined with force and torque support evidence, the system determines joint angle deviation, angular velocity abnormality, and torque abnormality, identifies the corresponding type of movement disorder, and further includes: During the gait swing phase, if the maximum flexion value of the knee joint angle in the joint motion state data is lower than the preset flexion threshold, it is determined that there is insufficient knee flexion and extension. During the gait support phase, if the knee joint angle in the joint motion state data exceeds the preset upper limit of extension and shows a backward bending trend, and the force and torque support evidence related to the knee joint shows abnormal force, it is determined that there is a knee retraction. When the knee joint angular velocity in the joint motion state data shows frequent pauses, sudden changes, or irregular high-frequency fluctuations within a continuous gait cycle, it is determined that there is a movement disorder of knee joint locking. Based on the movement disorder identification results, the target assist joint and the direction and magnitude of the assist torque are determined, movement assist control commands are generated, and active movement assist control is implemented through at least one of the following methods: joint drive assistance, torque compensation, trajectory amplification, mechanical limiting or damping, and lateral force compensation, to guide the patient to complete preset rehabilitation training movements. This also includes: When the movement disorder identification result indicates that there is insufficient knee flexion and extension, the knee joint is set as the target auxiliary joint, and an auxiliary torque is applied along the knee flexion direction during the gait swing phase, and the knee flexion angle is amplified within a preset range. When the movement disorder identification result indicates the presence of hyperextension of the knee, the knee joint is set as the target auxiliary joint, and a limiting auxiliary torque is applied along the knee flexion direction during the gait support phase to suppress hyperextension and hyperbending of the knee joint. When the movement disorder identification results indicate the presence of knee joint slack, rhythmic, small-amplitude flexion-extension auxiliary torques are applied to the knee joint during continuous gait cycles to improve the continuity and smoothness of knee joint angle and knee joint angular velocity.

2. The method for limb movement disorder recognition and active movement assistance control based on computer vision according to claim 1, characterized in that, Based on the spatial location data, construct multi-segment vectors of the limbs and calculate the angle between the vectors, including: Using the three-dimensional coordinates of the shoulder joint, elbow joint, wrist joint and torso point in the spatial location data, construct the upper arm vector from the shoulder joint to the elbow joint, the forearm vector from the elbow joint to the wrist joint and the torso vector from the torso point to the shoulder joint. Calculate the angle between the upper arm vector and the torso vector, and the angle between the upper arm vector and the forearm vector, to obtain the shoulder joint angle and the elbow joint angle; Based on the changes in the shoulder joint angle and elbow joint angle over time, the shoulder joint angular velocity and elbow joint angular velocity are obtained respectively, so that the joint motion state data includes at least the shoulder joint angle, shoulder joint angular velocity, elbow joint angle, and elbow joint angular velocity.

3. The method for limb movement disorder recognition and active movement assistance control based on computer vision according to claim 1, characterized in that, Constructing multi-segment vectors of limbs based on the spatial location data and calculating the angle between the vectors, further includes: Using the three-dimensional coordinates of the hip joint, knee joint, ankle joint, and toe points in the spatial location data, construct the thigh vector from the hip joint to the knee joint, the lower leg vector from the knee joint to the ankle joint, and the foot segment vector from the ankle joint to the toe points; Calculate the angle between the thigh vector and the calf vector, and the angle between the calf vector and the foot segment vector to obtain the knee joint angle and the ankle joint angle. Based on the changes of the knee joint angle and the ankle joint angle over time, obtain the knee joint angular velocity and the ankle joint angular velocity, respectively. The hip joint angle and hip joint angular velocity are determined based on the positional relationship of the hip joint in the spatial position data, so that the joint motion state data includes at least the hip joint angle, hip joint angular velocity, knee joint angle, knee joint angular velocity, ankle joint angle, and ankle joint angular velocity.

4. The method for limb movement disorder recognition and active movement assistance control based on computer vision according to claim 1, characterized in that, Based on the joint motion data and combined with force and torque support evidence, joint angle deviation, angular velocity abnormality, and torque abnormality are determined, and the corresponding movement disorder type is identified, including: In the joint motion state data, when the shoulder joint angle and shoulder joint angular velocity are inconsistent with the preset shoulder joint motion range and change pattern, and the displacement of the trunk point in the spatial position data determines that the trunk exceeds the preset range in the vertical or forward and backward directions, it is determined that there is a compensatory behavior of the trunk such as shrugging or the trunk leaning forward or bending to the side. In the joint motion state data, when the elbow joint angle does not reach the expected range within a preset time, or the elbow joint angle change trend is opposite to the preset target direction, and the elbow joint angular velocity shows a significant decrease or sudden change, the movement disorder of elbow joint flexion and extension or abnormal bending is determined by combining the force and torque support evidence. In the joint motion state data, when the joint angle of the wrist joint relative to the forearm continuously exceeds the preset normal range, or when the wrist movement trajectory obtained according to the spatial position data deviates from the target direction by more than a preset threshold, it is determined that there is a movement disorder of abnormal dorsiflexion, palmar flexion or deviation of the wrist joint.

5. The method for limb movement disorder recognition and active movement assistance control based on computer vision according to claim 1, characterized in that, Based on the joint motion state data, and combined with force and torque support evidence, the system determines joint angle deviation, angular velocity abnormality, and torque abnormality, identifies the corresponding type of movement disorder, and further includes: During the gait swing phase, if the ankle joint angle in the joint motion state data does not reach the preset dorsiflexion angle, and the foot segment is determined to be in a toe-down posture based on the spatial position data, foot drop is determined to exist. During standing or gait progression, if the ankle joint angle in the plantar flexion direction in the joint motion state data continuously exceeds a preset range, and the force and torque support evidence related to the ankle joint indicates instability in weight-bearing, it is determined that there is excessive plantar flexion of the ankle joint. When the foot segment is determined to deviate continuously from the direction of inversion or eversion relative to the ground normal direction based on the spatial position data and exceeds a preset range, it is determined that there is a movement disorder of ankle inversion or eversion.

6. The method for limb movement disorder recognition and active movement assistance control based on computer vision according to claim 1, characterized in that, Based on the movement disorder identification results, the target assist joint and the direction and magnitude of the assist torque are determined, movement assist control commands are generated, and active movement assist control is implemented through at least one of the following methods: joint drive assistance, torque compensation, trajectory amplification, mechanical limiting or damping, and lateral force compensation, to guide the patient to complete preset rehabilitation training movements, including: When the movement disorder identification results indicate the presence of shoulder shrugging or trunk compensation behavior, reduce the auxiliary force along the trunk lifting or forward leaning direction, and adjust the auxiliary force to target the elbow joint as the auxiliary joint and apply auxiliary torque along the elbow joint flexion and extension direction; When the movement disorder identification result indicates that there is limited flexion and extension or abnormal bending of the elbow joint, the elbow joint is set as the target auxiliary joint. The direction and magnitude of the auxiliary torque are determined according to the deviation between the elbow joint angle and the elbow joint angular velocity and the preset target, so that the elbow joint movement approaches the preset target trajectory. When the movement disorder identification result indicates the presence of abnormal dorsiflexion or palmar flexion of the wrist joint, the wrist joint is set as the target auxiliary joint, and an auxiliary torque is applied at the end-effector position to counteract the abnormal dorsiflexion or palmar flexion, so that the wrist joint is kept in a near-neutral position.

7. The method for limb movement disorder recognition and active movement assistance control based on computer vision according to claim 1, characterized in that, Based on the movement disorder identification results, the target assist joint and the direction and magnitude of the assist torque are determined, movement assist control commands are generated, and active movement assist control is implemented through at least one of the following methods: joint drive assistance, torque compensation, trajectory amplification, mechanical limiting or damping, and lateral force compensation, to guide the patient to complete preset rehabilitation training movements. This also includes: When the movement disorder identification result indicates the presence of foot drop, the ankle joint is set as the target auxiliary joint, and an auxiliary torque is applied along the dorsiflexion direction of the ankle joint during the gait swing phase to lift the foot and reduce the risk of dragging. When the movement disorder identification result indicates that there is excessive plantar flexion of the ankle joint, the ankle joint is set as the target auxiliary joint, an upper limit of the auxiliary torque or equivalent damping is set in the plantar flexion direction, and support is provided in the dorsiflexion direction of the ankle joint when weight-bearing is required; When the movement disorder identification result indicates the presence of ankle inversion or eversion, the ankle joint is designated as the target auxiliary joint, and a lateral auxiliary force or limiting auxiliary torque is applied in the inversion or eversion direction to maintain balanced contact of the sole of the foot.

8. The method for limb movement disorder recognition and active movement assistance control based on computer vision according to claim 1, characterized in that, Also includes: During multiple rehabilitation training sessions, the intent intensity, compensation index, and corresponding motor assist control commands in the motor impairment recognition results obtained from each training session are recorded. In subsequent training sessions, the selection of the target assist joint and the direction and magnitude of the assist torque are adaptively adjusted based on the recorded content to optimize the active motor assist control effect.

Images