104 results about "Gait analysis" patented technology

The invention discloses a video gait analysis-based asthenia syndrome evaluation method, medium and equipment, and the method comprises the steps: firstly, synchronously collecting gait videos of different visual angles through a plurality of cameras, and extracting 2D joint point sequences of all visual angles through a stacked hourglass network; then, a high-precision 3D joint point time sequence is reconstructed through a multi-view fusion algorithm, depth features are extracted through a residual connection network, and data of all view angles are dynamically weighted and fused based on the shielding rate and the confidence coefficient; performing sliding window segmentation and downsampling on the 3D sequence, and performing action classification by using an LSTM time sequence model; and finally, key motion parameters are extracted from a classification result to calculate a weakness score, and weakness grade evaluation is realized. According to the method, the problem of single-view shielding is solved through multi-view 3D reconstruction, the evaluation precision is remarkably improved by combining dynamic weighted fusion and time sequence modeling, and compared with a traditional method, the method has the advantages of being non-contact, low in cost and high in objectivity, and is suitable for large-scale screening of community and family environments.

The invention discloses a general electromyographic signal processing method and system based on a large self-supervised model. The general electromyographic signal processing method comprises the following steps: step 1, acquiring a multi-source original multi-electrode channel EMG signal X from an electromyographic acquisition device; and finally, performing data unification processing, and finally converting into a space-time activity diagram with a fixed size of 224 * 224. On the basis of the space-time activity diagram and the fatigue state mark, constructing an AEMG for training according to heterogeneous unlabeled EMG data collected by a collection device; performing light-weight Adapter layer fine adjustment on the pre-trained large myoelectricity model to adapt to gesture recognition muscle force regression gait analysis or rehabilitation evaluation downstream tasks; aiming at the problem that the dimension and the structure of myoelectricity data are not matched due to different acquisition devices, acquisition parts and acquisition tasks, original signals are converted into space-time activity diagrams in a unified format through data unification processing, device differences are represented by combining a sensor embedding module, effective alignment of cross-source data is achieved, and the accuracy of the data is improved. And a basis is provided for large-scale data utilization.

The invention provides a gait analysis method and an early warning system based on multi-source data fusion, three types of original signals are collected through a wearable inertial sensor, a plantar pressure insole and an edge calculation camera, and multi-dimensional motion characteristic parameters are fused through wavelet denoising, low-pass filtering, interpolation alignment and data consistency correction, so that the gait analysis method based on multi-source data fusion is realized. And constructing a user individualized gait feature prototype library. The method further adopts a dynamic causal graph network to model a motion relation between joints, determines an abnormal coupling mode based on causal weight and historical reference, and combines activity context and Bayesian rules to generate a dynamic threshold value to realize risk grading early warning, so that heterogeneous data collaborative analysis precision and abnormal gait detection sensitivity are improved, and the method is suitable for large-scale popularization and application. And support is provided for gait health monitoring and personalized risk management and control under multiple scenes.

The invention discloses a wearable plantar pressure and three-dimensional gait analysis system, and relates to the technical field of gait analysis, the system comprises a wearable in-shoe plantar pressure analysis subsystem and a three-dimensional gait analysis subsystem; the wearable in-shoe plantar pressure analysis subsystem comprises a pressure sensor module, a pressure integration module, an intelligent transmission module, a detection software module, a power supply module, an instantaneous pressure and balance detection module, a standing balance detection module, a balance and gait detection module and a cloud server; the three-dimensional gait analysis subsystem comprises a hardware unit and a software unit; according to the invention, a wearable plantar pressure and three-dimensional gait analysis collaborative system is constructed, bidirectional verification compensation is realized by means of data fusion of two subsystems, and traditional single-dimensional limitation is broken; pressure sensing and a double-view reconstruction technology are fused, data are dynamically captured, and bidirectional error correction is carried out; the limitation of traditional equipment is solved, the evaluation accuracy and robustness are improved, and a quantitative basis is provided for clinical diagnosis, rehabilitation and the like.

The invention relates to the technical field of behavior feature recognition, in particular to a beef cattle oestrus state monitoring method based on dynamic gait analysis. According to the method, multi-source data acquisition, such as dynamic gait video and body temperature data, video preprocessing, such as frame extraction, denoising, abnormal frame recognition and restoration, target tracking, dynamic gait characteristic parameter extraction, such as step length, step frequency, step speed, joint angle change and body gravity center offset, and life data acquisition, such as diet, body weight change and drinking water. A large oestrus monitoring and recognition model integrating attitude analysis, behavior analysis, living state analysis and an integration module is constructed, and after training and iterative optimization, accurate judgment of oestrus, non-oestrus and wig oestrus states of beef cattle is achieved in combination with ear tag identity recognition. By monitoring the dynamic gaits and behavior modes of the beef cattle and combining daily life data of the beef cattle, the problem of misjudgment caused by wig oestrus is greatly avoided, and the monitoring accuracy is improved.

The present invention relates to a method for creating an individualized machine learning inference model. In accordance with the invention, the aforementioned method and a related system involve a motion capture device adapted to be worn by a user. The motion capture device is adapted to acquire measurements, which are used to compute a first estimate of one or more gait parameters. Next, a database is accessed that contains previously collected observations of gait data and the first estimate is compared to the previously collected observations of gait data. Finally, the subset of previously collected observations of gait data that is most informative for the particular user is identified and the individualized machine learning inference model can be developed using the identified subset of previously collected observations of gait data.

The invention discloses a lumbar postoperative functional recovery evaluation method based on gait analysis, and the method comprises the steps: collecting a multi-modal gait multi-source signal, and building high-quality space-time synchronous multi-modal gait data through standardization processing and abnormity elimination; further extracting multi-point features such as an action sequence, pressure and myoelectricity, and realizing deep association between gait features and clinical evaluation indexes by adopting graph structure fusion and knowledge graph mapping; a graph neural network and an attention mechanism are introduced, the causal relationship between gaits and lumbar function recovery is reasoned, self-supervised dynamic optimization is performed according to individual differences, the objectivity, interpretability and adaptive ability of rehabilitation evaluation can be improved, and the rehabilitation accuracy is improved. And reliable data basis and causal traceability are provided for medical decision and personalized rehabilitation.

The invention discloses a six-dimensional force measurement matrix system and method for multi-terrain gait analysis of a humanoid robot. The system comprises a modular terrain simulation platform, a six-dimensional force measurement matrix module, a data acquisition and synchronization module and robot gait performance analysis software. The modular terrain simulation platform comprises a rigid leveling module, a slope module and a step module; the six-dimensional force measurement matrix module comprises a plurality of six-dimensional force measurement plates; the data acquisition and synchronization module acquires synchronous matrix data of each six-dimensional force measurement plate; and the robot gait performance analysis software calculates key kinetic parameters and time-space parameters and generates a comprehensive report. According to the invention, three terrains of a rigid flat ground, a slope and steps can be simulated, force and torque of the humanoid robot walking on the terrains are continuously and synchronously acquired through the measurement matrix, and comprehensive, real and accurate evaluation of gait functions is realized. And high-precision and multi-dimensional quantitative evaluation data are provided for gait control algorithm development, dynamic performance calibration and mechanical foot design of the robot.

The embodiment of the invention provides an actor recognition method, system and device based on ViT gait analysis and a medium, and belongs to the technical field of gait recognition. The method comprises the following steps: acquiring behavior video data of a target object; performing background subtraction processing on the behavior video data to obtain a binary image of the gait of the target object; inputting the binary image into a feature analysis model, wherein feature analysis is constructed and formed based on Transform; performing attitude feature extraction through a double-path parallel multi-head attention module of the feature analysis model, fitting a feature weight of the attitude feature through a feature average fusion module, and outputting an embedded feature vector; and comparing the embedded feature vector with a preset feature vector, and identifying the identity of the target object according to a comparison result. The embodiment of the invention aims to improve the accuracy of performing actor identity recognition through gaits.

The invention discloses a gait analysis and posture correction intelligent insole suitable for high-weight crowds and a preparation method of the gait analysis and posture correction intelligent insole. The intelligent insole comprises a composite functional layer, an electrode layer and a packaging layer, and the composite functional layer comprises a linear elastic gasket and a sensing material arranged in an opening area of the linear elastic gasket. The sensing material adopts a wedge-shaped structure design, and the effective contact area between the sensing material and the electrode can be linearly changed along with the compression displacement under the constraint action of the linear elastic washer, so that the high-linearity electrical response of a pressure signal is realized. And the adjacent sensing units are physically isolated by the linear elastic washers, so that the crosstalk phenomenon in the pressure sensing array is effectively reduced. Through linear regulation and control of the linear elastic gasket on mechanical response and cooperative modulation of the wedge-shaped structure sensing material on electrical response, stable and high-linearity plantar pressure detection is achieved under the condition of high plantar load, and the device is suitable for gait analysis and posture correction of high-weight people in the states of standing, walking, running and the like.

The invention relates to the technical field of intelligent monitoring equipment, in particular to a radar point cloud target detection system and method based on multi-modal space-time fusion. Comprising the following steps: at least two radar transceivers synchronously collect echo signals of a target at different visual angles, and establish a three-dimensional coordinate system; based on the three-dimensional coordinate system of the target points, the target points of each time slice are clustered, a coordinate set of point cloud clustering is obtained, and whether the point cloud gravity center of each detection target is displaced or not is judged; if the detected target is displaced, capturing a space trajectory of a target point based on the barycentric coordinates, and performing gait analysis on the detected target; and if the detection target does not displace, judging the body posture of the detection target. The method has the advantage of low cost, reliable radar point cloud can be realized, the defects that the traditional point cloud needs multi-antenna MIMO and the cost is high are overcome, body point cloud modeling in the walking process is realized, meanwhile, posture body point cloud and vital sign data are jointly verified, and the reliability is enhanced.

The present disclosure provides a gait analysis method and system, and an apparatus for improving a walking obstacle. The method includes: acquiring three-axis acceleration data and three-axis angular velocity data collected by an inertial sensor, and acquiring pressure data collected by a pressure sensor; performing a quaternion operation on the three-axis acceleration data and the three-axis angular velocity data to acquire three-axis acceleration and a three-axis Euler angle corresponding to a ground coordinate system; identifying a swinging state and a stationary state of feet based on the three-axis acceleration data and the pressure data; analyzing based on the three-axis acceleration, the three-axis Euler angle, and the swinging state and the stationary state of the feet to acquire gait parameters related to a straight walking process, a turning processing, a feet to ground angle, and a feet tremor; and uploading the gait parameters to a server.

This utility model discloses a foot pressure gait device for foot assessment, relating to the field of analytical equipment technology. The foot pressure gait device includes: a monitoring module comprising a housing and a data acquisition unit mounted on the housing; and a buffer pad connected to one side of the housing via a connecting part and capable of flipping relative to the housing. When the buffer pad is flipped to a preset position, the buffer pad and the housing are arranged in upper and lower layers. The technical solution provided by this utility model can solve the problem of insufficient constraint between the gait analyzer and the buffer pad, which leads to an increased distance between the buffer pad and the gait analyzer during use, requiring multiple adjustments of the buffer pad.

Provided is a gait analysis device and method. The gait analysis device may include an input unit that receives a user's gait sound data, and a gait analysis unit that derives the user's current gait information by analyzing the gait sound data.

The invention discloses a gait analysis device and method based on infrared data and video influence data. The method specifically comprises the following steps: synchronously obtaining front gait video data, side gait video data and infrared image data of a target to be detected; based on the front gait video data, image preprocessing is executed, key points are detected, and then the knee joint introversion angle, the foot rotation angle, the trunk roll amplitude and the step width of the to-be-detected target are calculated according to the key points to obtain the knee joint introversion angle, the foot rotation angle, the trunk roll amplitude and the step width of the to-be-detected target. Meanwhile, the human body posture is obtained based on the front gait video data and the side gait video data, the joint space coordinates are constructed based on the infrared image data, and the human body posture is put into the joint space coordinates for cross validation so as to ensure the accuracy of the obtained various parameters. Through fusion of multi-dimensional data, gait features can be reflected more comprehensively, and a comprehensive and accurate gait analysis result is finally generated through integration.

The invention provides a walking data filtering method and related equipment. The method comprises the following steps: traversing all obtained walking data matrixes, and determining a maximum value corresponding to each coordinate point to obtain a maximum value matrix; traversing four edges of the maximum value matrix, and determining edge points; the edge point is a first non-zero coordinate point during traversal; based on the edge points, determining a filtering area by using a flood filling method; and filtering the walking data matrix based on the filtering area. According to the embodiment of the invention, through fitting the maximum pressure matrix, filtering the edge abnormal data and adaptively adjusting the processing range, the accuracy and reliability of the plantar pressure data are improved, individual differences are adapted, and the gait analysis effect is optimized.

This invention discloses a gait analysis method and apparatus, relating to the field of data processing. It addresses the problems of existing gait analysis methods, such as high cost, complex operation and maintenance, and the interference of reflective markers / sensors with the test subject's natural gait. The method includes: acquiring temporal initial depth images simultaneously acquired by at least two depth image acquisition devices; processing a preset original skeleton model based on the temporal initial depth images to obtain the test skeleton of the subject and the first motion trajectory of each feature point of the test skeleton; matching the test skeleton with a preset original musculoskeletal model to obtain a test musculoskeletal model that conforms to the body shape characteristics of the subject; acquiring the second motion trajectory of each joint point of the test musculoskeletal model; and performing gait analysis calculations on the subject based on the second motion trajectory of each joint point of the test musculoskeletal model to obtain the average dynamic parameters, average kinematic parameters, and average spatiotemporal parameters of the subject's gait movement.

A gait analysis device, a gait analysis method, and a gait analysis program. In the gait analysis device, a step frequency change with respect to a running speed is acquired with respect to running of a subject. A step length change with respect to a running speed is acquired with respect to running of the subject. A determination section (80) calculates a principal component score from the slope of the step frequency change and the slope of the step length change of the subject, based on a principal component analysis model that is generated in advance based on measured values of a plurality of runners, and determines which of a plurality of gait types including a stride type and a step frequency type the running of the subject conforms to, based on the calculated principal component score.

The invention discloses a self-powered plantar pressure monitoring and gait analysis system integrated with a convolutional neural network. The self-powered plantar pressure monitoring and gait analysis system comprises a flexible insole type sensor module, a signal acquisition unit and a CNN analysis module. The sensor module adopts a liquid metal and polydimethylsiloxane composite porous sponge structure, and realizes sole dynamic pressure sensing through a three-dimensional communicated pore network; the signal acquisition unit is integrated with an LMS adaptive filtering algorithm and can dynamically filter motion noise and electromagnetic interference; and the CNN analysis module fuses the multi-modal feature extraction unit, the bidirectional LSTM network and the attention mechanism to realize end-to-end fusion analysis of plantar pressure, inertial sensing and thickness deformation data. The system innovatively constructs a'pressure-thickness-inertia 'multi-physics field coupling model, eliminates environmental interference through a temperature compensation unit, adopts a three-layer one-dimensional convolution structure and a dynamic weight distribution mechanism to improve gait recognition precision, and can be widely applied to the fields of rehabilitation medicine, sports biomechanics and the like.

Disclosed is a gait analysis device using artificial intelligence (AI) technology, according to some embodiments of the present invention. The gait analysis device may comprise: a camera unit for capturing an image of the gait of a target user in response to a user interaction through a display unit; a gait analysis unit for generating a gait analysis result obtained by analyzing the gait of the target user on the basis of the captured gait image, wherein the gait analysis result includes at least one of a stride length, a gait speed, a swing angle of both arms, an upper body angle, a hip joint angle of both legs, or a knee angle of the target user; and the display unit for outputting the gait analysis result.

The invention relates to the technical field of image monitoring, in particular to an elderly patient behavior image monitoring and falling risk analysis system and method, and the method comprises the steps: a front-end collection module collects a time sequence image of an activity area of an elderly patient; the posture detection module analyzes and extracts three-dimensional posture information of the elderly patient based on a differential geometry theory, and comprises a key point detection unit, a manifold mapping unit and a constraint optimization unit; the gait analysis module processes attitude parameters through a parameter extraction unit, a time sequence track unit and a curvature analysis unit; the risk assessment module calculates a fall risk level based on the gait feature data; according to the invention, an APMK-HCW algorithm is innovatively applied to realize high-precision 3D attitude estimation under a monocular camera, geodesic curvature analysis is introduced to quantify gait stability, and a personalized baseline assessment and adaptive optimization mechanism is adopted to realize early precise early warning of the falling risk of the elderly patient.

An animal gait analysis is provided and includes a testing platform, a plurality of footprint signal modules mechanically connectable end-to-end and electrically connectable to form a walking path of a predetermined configuration, a testing enclosure disposed above the walking path, and a control device electrically connected to the footprint signal modules, wherein the testing enclosure comprises at least two side panels disposed opposite each other, at least one obstacle, and at least one movable partition, the spacing between the side panels is automatically adjusted by a drive mechanism to accommodate test objects of different body types, the obstacle is selectively connected to a surface of the footprint signal modules, and the movable partition is selectively connected to a surface of the footprint signal modules.

The invention relates to a method (2000, 3000, 4000) for calibrating a posture / gait analysis system (1). The system (1) comprises an insole (2) equipped with a plurality of capacitive pressure sensors (4), and a control unit (5) connected to the pressure sensors (4). The method includes the following steps. First, signals provided by a pressure sensor (4) are acquired (2000), said sensor being subjected to a pressure varying between a first value and a second value, where each signal is indicative of a capacity value of the sensor, which capacity value depends on the pressure applied thereto. For each pressure sensor, a polynomial relationship is to be defined between an estimate of the pressure experienced by the sensor (4) and a change in the capacity of the sensor; a plurality of sets of coefficients of a polynomial are calculated (3001-3011) that minimize a norm of a residual between the pressure estimate and a corresponding pressure applied on the sensor (4), wherein each set of coefficients is calculated for a polynomial relationship between a minimum order and an optimized maximum order. An averaging of the minimization results obtained by each sensor for the same order of the polynomial relationship is then performed (3011). The set of coefficients and respective orders of the polynomial relationship associated with the minimum value between the calculated averages are selected (3012, 3013) and stored (3014, 3015) in the control unit (5).

The invention provides a gait analysis method, a related device and a computer storage medium, and the method comprises the steps: carrying out the real-time detection through a multi-dimensional force sensor, obtaining the original data of two feet, carrying out the multi-dimensional force decoupling of the original data of the two feet, obtaining the N-dimensional prediction force sequence data of the two feet, carrying out the gait analysis based on the N-dimensional prediction force sequence data of the two feet, and obtaining the gait analysis result. And a gait analysis result is obtained, so that real-time and accurate analysis and monitoring of a complex gait mode of the user are realized.

The invention discloses a gait monitoring method and system based on a carbon nanotube flexible pressure sensor. The method comprises the following steps: receiving pressure distribution data acquired by the carbon nanotube flexible pressure sensor when a user walks; performing gait analysis on the pressure distribution data by using a hybrid neural network, judging a gait type of the user, and evaluating a walking posture; according to the gait type and the evaluation result, the sensitivity setting of the flexible pressure sensor is automatically adjusted to optimize the data acquisition process; and generating a personalized gait report, and sending the gait report to the user. By utilizing the embodiment of the invention, the limitation of the existing gait monitoring technology can be improved, and more accurate and personalized gait analysis can be provided to meet the requirements of different users and application scenes.

By using the helical axis in the knee joint movement of subjects during walking, we perform gait analysis that can be used to detect early-stage osteoarthritis of the knee. [Solution] A gait analysis method comprising the steps of: calculating the helical axis of the knee joint based on motion data of the subject's lower limbs during walking; extracting the flexion phase and extension phase during the stance phase of the subject's gait cycle; and obtaining an evaluation value to assess the condition of the knee by quantifying the variability of the helical axis group in one or both of the flexion phase and the extension phase.

The application relates to the medical technical field and discloses an intelligent gait analysis auxiliary diagnosis system for knee joint function, which comprises a data acquisition module, a 3D human posture modeling module, a gait feature extraction module, a gait feature measurement and analysis module, a deep learning analysis and diagnosis module, an explanatory model and user interaction module, a system integration module and a data management and storage module; the data acquisition module collects human gait video data through a multi-view camera system. The non-contact multi-view camera technology and the artificial intelligence algorithm are adopted to reduce the dependence on expensive equipment and professional operation, reduce the deployment and maintenance cost of the system, enable small and medium-sized hospitals to carry out medical services related to gait analysis, and through the non-contact data acquisition mode, the step of pasting mark points on the patient is omitted, the operation process is simplified, the dependence on professional medical staff is reduced, and the work efficiency is improved.

The invention relates to the technical field of intelligent wearable equipment, and particularly discloses a multi-mode biosensor monitoring sock system. The system comprises a flexible sock body, a multi-mode sensor array integrated on the flexible sock body, a master control synchronization module and a data processing module. The master control synchronization module generates global hardware synchronization pulses based on a single high-precision crystal oscillator, directly triggers analog-to-digital converters of all pressure, inertia and myoelectricity sensor channels, and realizes synchronous sampling of a hardware level. And the data processing module gives a uniform timestamp to the synchronous data stream and then sends the synchronous data stream. According to the method, high-precision time alignment of multi-modal signals is ensured, a reliable basis is provided for subsequent data fusion and gait analysis, and the power consumption and complexity of the system are reduced.

The invention relates to the technical field of artificial intelligence and self-powered wearable sensing, in particular to an intelligent insole based on a self-powered sensor array and a sole pressure behavior recognition method thereof. The system comprises a self-energized sensor array, a signal acquisition and processing module and a data analysis module which are arranged in an insole, the self-energized sensor array is composed of a plurality of friction nanometer power generation units which are arranged in an array mode, and the friction nanometer power generation units are arranged in the forefoot area, the arch area and the heel area of the insole respectively. Electric signals can be generated under the action of plantar pressure or impact without external power supply. The system performs synchronous acquisition, analog-to-digital conversion and normalization processing on the electric signals output by the friction nanometer power generation units to form multi-channel plantar pressure characteristic signals, and realizes reconstruction of plantar pressure distribution and identification analysis of behavior states based on the characteristic signals. The system can effectively reflect stress differences of different areas of the sole, can be used for distinguishing various motion behaviors such as walking and running, realizes self-energy-supply acquisition, visual perception and behavior recognition of sole pressure information, and has good application prospects in the fields of motion monitoring, gait analysis, health assessment and the like.

A computer implement method of gait analysis comprising carrying out video analysis using augmented or virtual reality markers without the use of external sensors or markers which allows for objective longitudinal comparison of gait analyses and provides a flexible system allowing multiple gait analysis test to be carried out using only a single test system.