CN219000294U - Virtual evoked and walking gait evaluation system for parkinsonism - Google Patents
Virtual evoked and walking gait evaluation system for parkinsonism Download PDFInfo
- Publication number
- CN219000294U CN219000294U CN202221531879.9U CN202221531879U CN219000294U CN 219000294 U CN219000294 U CN 219000294U CN 202221531879 U CN202221531879 U CN 202221531879U CN 219000294 U CN219000294 U CN 219000294U
- Authority
- CN
- China
- Prior art keywords
- virtual
- walking
- subject
- data
- gait
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The utility model relates to a virtual induction and walking gait evaluation system for parkinsonism, which is technically characterized in that: the system comprises a virtual induction and walking assisting robot system, a data collection system and a data analysis system, wherein a subject feels a VR virtual scene provided by the virtual induction and walking assisting robot system and walks by means of the walking assisting robot, the data collection system collects human skeleton information, physiological signals and motion signals of the subject and transmits the human skeleton information, physiological signals and motion signals to the data analysis system, and the data analysis system analyzes and obtains a walking function assessment result according to received data. According to the utility model, the brain function of the subject is mobilized through the virtual reality scene, so that the possible functional deficiency of the subject can be exposed; meanwhile, the skeleton information is effectively combined with information such as surface electromyographic signals and plantar pressure, so that objective and quantitative evaluation functions of gait disorder of a subject are realized, and the method has the characteristics of convenience, easiness in operation and control, strong data objectivity and the like.
Description
Technical Field
The utility model belongs to the technical field of medical equipment, relates to a parkinsonism symptom evaluation system, and particularly relates to a parkinsonism virtual induction and walking gait evaluation system.
Background
Parkinson's disease is a neurodegenerative disease, and its symptoms are characterized by: progressive progression of the condition and difficulty in early diagnosis. At present, the walking gait of parkinsonism is evaluated usually according to questionnaire form and subjective judgment of doctors, so that the symptom of patients is evaluated, the misdiagnosis rate is high, and a data objectivity quantitative evaluation means is lacked.
Since the dyskinesia disorder of early parkinsonian patients is not apparent per se, it makes clinical studies of parkinsonian dyskinesia very difficult and extremely occasional. How to find early gait disorder of parkinsonism patients as early as possible is of great importance for diagnosing and treating parkinsonism patients, and therefore, there is an urgent need for a device capable of effectively assessing parkinsonism gait disorder.
Clinical experience shows that under a specific scene or a complex task, the brain function is mobilized by the specific scene or task, so that the motion control capability of the patient affected by the disease is more likely to be displayed, and the motion control capability of the patient can be particularly shown in the aspects of limb motion performance such as walking motion, surface electromyographic signals and the like. Therefore, by the virtual reality technology, a specific virtual scene or (and) training task is created, so that the early parkinsonism patient dyskinesia is more likely to be induced, and the early diagnosis and quantitative evaluation are facilitated.
Disclosure of Invention
The utility model aims to overcome the defects of the prior art and provide a virtual induction and walking gait evaluation system for parkinsonism, which is reasonable in design, accurate, reliable and convenient to use.
The utility model solves the technical problems in the prior art by adopting the following technical scheme:
the virtual induction and walking gait evaluation system comprises a virtual induction and walking assisting robot system, a data collection system and a data analysis system, wherein the virtual induction and walking assisting robot system and the data collection system are connected through a subject support, the subject feels a VR virtual scene provided by the virtual induction and walking assisting robot system and walks by means of the walking assisting robot, the data collection system collects human skeleton information, physiological signals and motion signals of the subject and transmits the human skeleton information, physiological signals and motion signals to the data analysis system, and the data analysis system analyzes and obtains a walking function evaluation result according to received data.
Further, the virtual induction and walking assistance robot system comprises a VR virtual scene interaction system and an auxiliary walking robot; the VR virtual scene interaction system adopts a virtual reality technology and builds a virtual scene inducing gait disturbance through a virtual reality development platform; the VR virtual scene interaction system adopts head-mounted VR equipment to provide visual and auditory feedback for a subject in a virtual environment; the assist robot provides walking assistance and protection to the subject.
Further, the VR virtual scene interaction system employs a programmable VR device that sets different virtual scenes according to user needs.
Further, the data collection system comprises a following robot carrying a tripod head camera and other physiological signals and motion signal sensors, wherein the following robot carrying the tripod head camera keeps a certain distance to follow a subject in an evaluation process, and human skeleton information is obtained according to video information analysis and is transmitted to the data analysis system; the other physiological signal and motion signal sensors are a myoelectric sensor and a plantar pressure sensor; the myoelectric sensor collects surface myoelectric signals of the subject and transmits the surface myoelectric signals to the data analysis system; the plantar pressure sensor collects plantar pressure dynamic distribution data of the subject and transmits the data to the data analysis system.
Further, the following robot carrying the pan-tilt camera adopts equipment capable of tracking a user and extracting user skeleton information and storing data; the plantar pressure sensor adopts plantar pressure collecting equipment.
Further, the myoelectric sensor measures the myoelectric signals of the leg and the muscle group related to walking exercise and is combined with skeleton information to evaluate the exercise function of the subject; the subject's motor functions include the severity of frozen gait symptoms and the severity of bradykinesia.
Further, the data analysis system analyzes and processes the video acquired by the following robot, extracts human skeleton information and skeleton key point information, and obtains a motion function evaluation result.
Further, the data analysis system carries out quantitative estimation according to human skeleton information, physiological signals and motion signals to obtain a subject motion function estimation result; the quantitative estimation is to obtain a real-time plantar pressure cloud picture according to plantar pressure dynamic distribution data acquired by plantar pressure sensors; and obtaining a walking function evaluation result according to the comprehensive myoelectricity time domain and frequency domain indexes and the plantar pressure cloud picture.
The utility model has the advantages and positive effects that:
according to the utility model, a virtual scene interaction system of VR is adopted to construct a scene which is easy to induce parkinsonism for a subject, symptoms can be actively induced and amplified, walking images, surface electromyographic signals and plantar pressure signals of a user are acquired and analyzed by following a robot, an electromyographic sensor and a plantar pressure insole, and skeleton information is effectively combined with information such as the surface electromyographic signals and plantar pressure to obtain an objective quantification result, so that objective quantification assessment function of gait disorder of the subject is realized, and the characteristics of convenience, easiness in operation, strong data objectivity and the like are achieved.
Drawings
FIG. 1 is a schematic diagram of a system connection of the present utility model;
FIG. 2 is a block diagram of a virtual induction and walking assist robot system of the present utility model;
fig. 3 is a schematic illustration of the process of the present utility model.
Detailed Description
Embodiments of the present utility model are described in further detail below with reference to the accompanying drawings.
A virtual induction and walking gait evaluation system for parkinsonism is shown in figure 1, and is formed by connecting a virtual induction and walking auxiliary robot system, a data collection system and a data analysis system. The evaluation system is connected through a subject support, in the evaluation process, the subject wears the head-mounted VR device (01) to feel a VR virtual scene, and under the consideration of walking assistance and safety guarantee of the subject, the subject walks by means of the walking assistance robot (02) in the evaluation process, meanwhile, physiological data information is acquired by the subject wearing the sole pressure insole (06) and the myoelectric sensor (05), motion data of the subject are tracked and shot through the following robot (04) carrying the cradle head camera (03), and comprehensive data integration of multiple time periods is carried out through the data analysis system, so that an evaluation result is finally obtained. The following describes three components of the system:
as shown in fig. 2, the virtual induction and walking assistance robot system includes a VR virtual scene interaction system, an assisted walking robot, and a head-mounted VR device. The VR virtual scene interaction system adopts a virtual reality technology, constructs a 3D scene through a virtual reality development platform, provides a virtual environment for a patient through head-mounted VR equipment, and gives a tight and narrow environment to a subject through constructing different virtual scenes such as a narrow door, a single bridge, a turning and the like, so that the gait disorder induction function is realized, and the symptom is amplified to be convenient to evaluate. The VR virtual scene interaction system adopts modeling construction virtual reality of VR and a virtual reality development platform to induce gait disorder of a patient, each time the test environment is consistent, the construction of VR scenes provides the same test scene for different test conditions, the variables of each test are controlled to a certain extent, and simultaneously, the VR technology is used for creating scenes to collect data in different states at different rehabilitation stages of the patient. Because the subject wears the head-mounted VR device, inconvenience may be brought to the vision and the actions of the subject, the auxiliary robot supported by the vitamin motor is provided for the subject, the speed can be controlled autonomously, and larger assistance is provided for assisting and protecting the walking of the subject.
The VR virtual scene interaction system is in wireless connection with the head-mounted VR device, and scenes constructed by the VR virtual scene interaction system can be displayed through the head-mounted VR device, and meanwhile cognitive tasks are issued to a subject, such as identifying simple geometric figures. The reason for adopting the structure is that: when a subject is tested, the likelihood of exhibiting gait disturbance characteristics is increased due to the simultaneous multitasking. Training scenes in the VR virtual scene interaction system can be adjusted according to different conditions of a subject, and tool software of the VR virtual scene interaction system is utilized to modify the training scenes in the scene development of the virtual reality development platform.
In this embodiment, the VR virtual scene system uses an oculus request 2 device from Meta corporation, which has a configuration of a processor i38100+, a graphics card gtx1065+, and a memory 16G, and is small and lightweight. The walking assisting robot adopts an intelligent walking aid of a Xinsong company and is used for assisting a subject to walk. The headset VR device may employ any of the headset VR devices on the market that have wireless communication capabilities.
As shown in fig. 1, the data collection system includes a following robot with a cradle head camera, a sole pressure insole worn by a subject, and a myoelectric sensor, and is used for collecting movement data of the subject and physiological data information of the subject, and the data collection system provides comprehensive body data of the subject for the data analysis system by collecting the multidimensional data. The data dimension is selected for acquisition because the symptoms can be reflected on limb movement and physiological performance when the subjects perform the double tasks of cognition and movement.
The following robot carrying the cradle head camera keeps a certain distance to follow the subject in the evaluation process, and video information is recorded through the camera. In this embodiment, the following robot uses a device (for example, a robomatos 1 device of DJI) capable of tracking, extracting skeleton information and storing data, which can autonomously recognize and follow a pedestrian, can also recognize various gestures, and can perform self-defined reaction, has four mecanum wheels, and can realize four-zone omnidirectional movement. The following robot can realize functions such as real-time shooting, autonomous tracking, emergency early warning and the like. When the physical movement condition of the subject is photographed in real time, the human skeleton is extracted by using an information extraction algorithm to obtain human skeleton information, and the human skeleton information is transmitted to a data analysis system.
The myoelectric sensor and the plantar pressure sensor are wearable sensor parts, and can acquire sEMG time domain signals and plantar pressure dynamic distribution data of a subject and transmit the sEMG time domain signals and plantar pressure dynamic distribution data to a data analysis system. In this embodiment, the myoelectric sensor adopts a surface myoelectric acquisition system (for example, a surface myoelectric acquisition system of Delsys) capable of collecting myoelectric signals, and the system can be externally connected with a myoelectric signal sensor to measure muscle signals of muscle groups related to leg and walking movement, and receive the muscle signals at an interface, so as to finally obtain data information of myoelectric signals, acceleration, speed, rotation and six axes in space. The plantar pressure sensor collects plantar pressure distribution data of a subject in the testing process, can perform static and dynamic measurement on the pressure distribution of any contact surface, can display the outline of the pressure distribution and various data in real time through visual and image two-dimensional and three-dimensional color images, and in the embodiment, adopts plantar pressure collecting equipment (for example, ZIGUM plantar pressure equipment), can synchronously record time parameters except the capturable pressure and the force, can display a force-time diagram and a pressure curve in real time, and can transmit data in real time.
As shown in fig. 1, the data analysis system extracts skeletal key points of a patient for human skeleton information acquired by the following robot, obtains a vectorized gait information sequence, and extracts parameters such as step length, swing arm angle, swing arm speed and the like from the vectorized gait information sequence. Since the key point information of different time points is not independent, valuable exercise information needs to be obtained according to the relationship between them and the change with time, and the walking skeleton is evaluated. In the embodiment, a machine learning algorithm is utilized to extract time-related features, and then prediction of a motion mode is obtained through the algorithm. The key point information is extracted and valuable motion information is obtained by adopting a conventional processing mode through existing software.
For the data acquired by the myoelectric sensor, the embodiment adopts the parameter of the relevant evaluation characteristic as an evaluation quantization index, carries out definition classification of different degrees on the result of the subject, and converts signals of speed, acceleration, angle and the like of the sensor into quantization indexes for evaluation, but the method is not limited to the indexes. In the process of calculating parameters of the relevant evaluation features, fourier transformation is first needed to convert a time domain signal of a sensor into a frequency domain signal, so as to obtain a Power Spectral Density (PSD) of the signal. The power spectral density reflects the distribution of the power of the signal at each frequency point, and the freezing index is the ratio of the area under the frozen gait region (high frequency part, 3-8 Hz) to the area under the normal gait region (low frequency part, 0-3 Hz) in the power spectral density curve. When a gait disturbance occurs in a subject, serious tremors of the limb occur, and the high frequency portion of the sensor signal including acceleration, joint angle, and the like increases. The freezing index reflects the severity of the patient's gait freezing by the ratio of high frequency to low frequency. For plantar pressure data, the embodiment adopts MATLAB to perform impurity removal treatment on the acquired plantar pressure dynamic distribution data, and a real-time plantar pressure cloud picture is obtained. And the data analysis system synthesizes the myoelectricity freezing index and the plantar pressure cloud picture to obtain a myoelectricity foot force evaluation result. The myoelectricity foot force evaluation result is realized by adopting a conventional processing mode through the existing software. The device for analyzing the data can be an onboard computer of the robot or a special device for uniformly processing the collected data.
The evaluation process of the utility model is as follows: because the early symptoms of the Parkinson disease are not obvious, the utility model carries out training induction by means of the virtual reality technology, and can carry out scene adjustment if the test requirement is changed. The subject wears the head-wearing VR device, wears the plantar pressure insole, attaches myoelectricity acquisition equipment to the muscle groups related to the exercise, which need to collect data, on the legs, and performs the test with the assistance of the auxiliary robot. The virtual reality induction part is a starting factor of the system, in the testing process, surface electromyographic signals, plantar pressure and walking images are collected to extract human skeleton information, and after data processing, the individual results of each subject are classified and evaluated to realize the walking evaluation effect.
The utility model is applicable to the prior art where nothing is mentioned.
It should be emphasized that the examples described herein are illustrative rather than limiting, and therefore the utility model includes, but is not limited to, the examples described in the detailed description, as other embodiments derived from the technical solutions of the utility model by a person skilled in the art are equally within the scope of the utility model.
Claims (8)
1. A virtual evoked and walking gait assessment system for parkinson's gait disorder, characterized by: the system comprises a virtual induction and walking assisting robot system, a data collection system and a data analysis system, wherein the virtual induction and walking assisting robot system and the data collection system are connected through a subject support, the subject feels a VR virtual scene provided by the virtual induction and walking assisting robot system and walks by means of the walking assisting robot, the data collection system collects human skeleton information, physiological signals and motion signals of the subject and transmits the human skeleton information, physiological signals and motion signals to the data analysis system, and the data analysis system analyzes and obtains a walking function evaluation result according to received data.
2. The virtual induction and walking gait assessment system of parkinson's gait disorder according to claim 1, wherein: the virtual induction and walking assisting robot system comprises a VR virtual scene interaction system and an assisting walking robot; the VR virtual scene interaction system adopts a virtual reality technology and builds a virtual scene inducing gait disturbance through a virtual reality development platform; the VR virtual scene interaction system adopts head-mounted VR equipment to provide visual and auditory feedback for a subject in a virtual environment; the assist robot provides walking assistance and protection to the subject.
3. The virtual induction and walking gait assessment system of claim 2, wherein: the VR virtual scene interaction system adopts programmable developed VR equipment, and different virtual scenes are set according to user needs.
4. The virtual induction and walking gait assessment system of parkinson's gait disorder according to claim 1, wherein: the data collection system comprises a following robot carrying a cradle head camera and other physiological signals and motion signal sensors, wherein the following robot carrying the cradle head camera keeps a certain distance to follow a subject in an evaluation process, analyzes according to video information to obtain human skeleton information and transmits the human skeleton information to the data analysis system; the other physiological signal and motion signal sensors are a myoelectric sensor and a plantar pressure sensor; the myoelectric sensor collects surface myoelectric signals of the subject and transmits the surface myoelectric signals to the data analysis system; the plantar pressure sensor collects plantar pressure dynamic distribution data of the subject and transmits the data to the data analysis system.
5. The virtual induction and walking gait assessment system of claim 4, wherein: the following robot carrying the cradle head camera adopts equipment capable of tracking a user and extracting user skeleton information and storing data; the plantar pressure sensor adopts plantar pressure collecting equipment.
6. The virtual induction and walking gait assessment system of claim 4, wherein: the myoelectric sensor measures the myoelectric signals of the leg and the muscle group related to walking exercise and is combined with skeleton information to evaluate the exercise function of the subject; the subject's motor functions include the severity of frozen gait symptoms and the severity of bradykinesia.
7. The virtual induction and walking gait assessment system of parkinson's gait disorder according to claim 1, wherein: the data analysis system analyzes and processes the video acquired by the following robot, extracts human skeleton information and skeleton key point information, and obtains a motion function evaluation result.
8. The virtual induction and walking gait assessment system of parkinson's gait disorder according to claim 1, wherein: the data analysis system carries out quantitative estimation according to human skeleton information, physiological signals and motion signals to obtain a subject motion function estimation result; the quantitative estimation is to obtain a real-time plantar pressure cloud picture according to plantar pressure dynamic distribution data acquired by plantar pressure sensors; and obtaining a walking function evaluation result according to the comprehensive myoelectricity time domain and frequency domain indexes and the plantar pressure cloud picture.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202221531879.9U CN219000294U (en) | 2022-06-20 | 2022-06-20 | Virtual evoked and walking gait evaluation system for parkinsonism |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202221531879.9U CN219000294U (en) | 2022-06-20 | 2022-06-20 | Virtual evoked and walking gait evaluation system for parkinsonism |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN219000294U true CN219000294U (en) | 2023-05-12 |
Family
ID=86250246
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202221531879.9U Active CN219000294U (en) | 2022-06-20 | 2022-06-20 | Virtual evoked and walking gait evaluation system for parkinsonism |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN219000294U (en) |
-
2022
- 2022-06-20 CN CN202221531879.9U patent/CN219000294U/en active Active
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| D’Antonio et al. | Validation of a 3D markerless system for gait analysis based on OpenPose and two RGB webcams | |
| Patel et al. | A wearable multi-modal bio-sensing system towards real-world applications | |
| Rocha et al. | Parkinson's disease assessment based on gait analysis using an innovative RGB-D camera system | |
| Chen | Human motion analysis with wearable inertial sensors | |
| Zhou et al. | Accurate recognition of lower limb ambulation mode based on surface electromyography and motion data using machine learning | |
| Lu et al. | Evaluation of classification performance in human lower limb jump phases of signal correlation information and LSTM models | |
| US20220287651A1 (en) | Method and system for analyzing biomechanical activity and exposure to a biomechanical risk factor on a human subject in a context of physical activity | |
| Salchow-Hömmen et al. | Emerging portable technologies for gait analysis in neurological disorders | |
| Prakash et al. | Identification of spatio-temporal and kinematics parameters for 2-D optical gait analysis system using passive markers | |
| CN114366559A (en) | Multi-mode sensing system for lower limb rehabilitation robot | |
| WO2022141894A1 (en) | Three-dimensional feature emotion analysis method capable of fusing expression and limb motion | |
| CN113066260A (en) | Parkinson's disease early warning system based on daily behavior analysis | |
| Ren et al. | Multivariate analysis of joint motion data by Kinect: application to Parkinson’s disease | |
| CN114366557A (en) | Man-machine interaction system and method for lower limb rehabilitation robot | |
| CN110801227B (en) | Method and system for testing three-dimensional color block obstacle based on wearable equipment | |
| CN219000294U (en) | Virtual evoked and walking gait evaluation system for parkinsonism | |
| Hewson et al. | The PARAChute project: remote monitoring of posture and gait for fall prevention | |
| CN113768471B (en) | Parkinson disease auxiliary diagnosis system based on gait analysis | |
| Gonzalez-Islas et al. | Human gait analysis based on automatic recognition: A review | |
| Nutakki et al. | Correlations of gait phase kinematics and cortical EEG: modelling human gait with data from sensors | |
| Zhao et al. | Global joint information extraction convolution neural network for Parkinson’s disease diagnosis | |
| US20240130636A1 (en) | Apparatus and method for motion capture | |
| Oluwadare | Gait analysis on a smart floor for health monitoring | |
| Sevcenco et al. | Motion tracking and learning in telerehabilitation applications | |
| Vilas et al. | Gait Analysis in Hereditary Amyloidosis Associated to Variant Transthyretin |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |