CN111000567B - Human body walking state identification method for wearable device and wearable device - Google Patents
Human body walking state identification method for wearable device and wearable device Download PDFInfo
- Publication number
- CN111000567B CN111000567B CN201911368933.5A CN201911368933A CN111000567B CN 111000567 B CN111000567 B CN 111000567B CN 201911368933 A CN201911368933 A CN 201911368933A CN 111000567 B CN111000567 B CN 111000567B
- Authority
- CN
- China
- Prior art keywords
- foot
- cluster
- threshold value
- displacement
- wearable device
- 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
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/112—Gait analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1123—Discriminating type of movement, e.g. walking or running
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Physiology (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a human body walking state identification method for a wearable device and the wearable device, wherein the method comprises the following steps: measuring the horizontal displacement, the vertical displacement and the steering angle of the foot of each gait cycle in the walking process of a user through the wearable device; identifying the turning and walking state of the user according to the steering angle; clustering the horizontal displacement and the vertical displacement of the feet of each step of the user through a clustering algorithm to form different clusters; the walking state of the cluster is identified according to the average value of the horizontal displacement and the vertical displacement in the cluster, and different states including different moving speeds, ascending and descending stairs, ascending and descending slopes and turning can be identified when a user walks. The invention utilizes the angular velocity and acceleration data acquired by the inertial sensor unit to calculate the lower limb displacement of the user so as to identify different walking states of the user, is convenient to use, is not limited by the field, has low cost, can identify the walking state of the user with high precision, and has higher reliability and better popularization prospect.
Description
Technical Field
The invention relates to a human body walking state identification method for a wearable device and the wearable device.
Background
The daily exercise monitoring can count the exercise amount of the human body and analyze the exercise capacity of the human body, and the daily exercise monitoring has a high application value. Wearable sensors are widely applied to the field of daily exercise monitoring as emerging technologies including an inertial measurement unit, an ultrasonic sensor, a miniature camera and the like, and the wearable sensors are small and small, low in price, free of time and space limitation, easy to popularize and the like. At present, a plurality of researches are carried out to identify different motion states of human bodies, including going up and down stairs, walking and the like, by using sensors placed on wrists and waists of the human bodies. However, the measured motion information is not directly related to the human motion state, so that the identification precision is not high.
Disclosure of Invention
The invention aims to solve the defects of low identification precision and the like in the prior art, and provides a human body walking state identification method for a wearable device and the wearable device.
Some of the nouns referred to in the present invention have the following meanings:
the gait cycle refers to the cycle of walking, taking the same foot as an example, the flat-foot stage (the surface of the foot is in full contact with the ground) is regarded as the beginning of the gait cycle, and then the foot lifts off the ground, steps forward, falls to the ground, and reaches the next flat-foot stage, which is regarded as the end of the gait cycle.
The horizontal displacement and the vertical displacement of the foot are the displacements of the foot in the horizontal direction and the vertical direction after the whole gait cycle.
The foot course angle is the orientation of the foot in the horizontal plane, and the foot steering angle is the change value of the course angle of the foot after the foot goes through a whole gait cycle.
The clustering algorithm is a statistical analysis method for solving the classification problem, and divides data into different clusters according to multiple characteristics of the data, wherein each cluster is a collection of data with certain common characteristics. The density-based DBSCAN clustering algorithm principle is that clusters are defined as the maximum set of points connected by density, and areas with high enough density can be divided into clusters, and the method specifically comprises the following steps: (1) detecting an object p which is not checked in the database, if the object p is not processed (not classified as a certain cluster or marked as noise), checking the neighborhood (the area with the distance p smaller than the radius of the neighborhood), if the number of included objects is not smaller than minPts (minimum number), establishing a new cluster C, and adding all points in the new cluster C into a candidate set N; (2) checking the neighborhood of all unprocessed objects q in the candidate set N, and adding the objects q to the candidate set N if at least minPts objects are contained; if q does not belong to any cluster, adding q to C; (3) repeating the step (2), and continuously checking the unprocessed objects in the N, wherein the current candidate set N is empty; (4) repeating steps (1) to (3) until all objects fall into a certain cluster or are marked as noise.
In order to solve the technical problem, the invention adopts the following specific technical scheme:
a human body walking state identification method for a wearable device comprises the following steps:
s1, measuring horizontal displacement, vertical displacement and steering angle of a foot in each gait cycle in a walking process of a user through wearable equipment;
s2, identifying the turning and walking state of the user according to the steering angle;
s3, clustering the horizontal displacement and the vertical displacement of the feet of each step of the user through a clustering algorithm to form different clusters;
and S4, identifying the walking state of the cluster according to the average value of the horizontal displacement and the vertical displacement in the cluster, including walking on the flat ground, ascending the stairs, descending the stairs, ascending the slope and descending the slope.
By adopting the technical scheme, the measured horizontal displacement, vertical displacement and steering angle in the gait cycle are directly related to the motion state of the user, the turning walking state is identified according to the steering angle, the identification precision is high, the walking state of the cluster is identified according to the average value of the horizontal displacement and the vertical displacement in the cluster, and the walking state is convenient, fast and high in precision.
As a further improvement of the present invention, the turning and walking state identification process includes the steps of:
s21, calculating a steering angle of the foot from the beginning of the gait cycle to the end of the gait cycle:
Δθ＝|θE-θS|
in the formula: delta theta is a steering angle thetaEIs the heading angle of the foot at the end of the gait cycle, θSIs the heading angle of the foot at the beginning of the gait cycle;
and S22, comparing the steering angle with a turning threshold value, and identifying the turning walking state if the steering angle is larger than the turning threshold value. By adopting the technical scheme, the method for measuring the steering angle is adopted to judge whether the vehicle is in a turning state, and the method is direct and accurate.
As a further development of the invention, the turning threshold is 25 °. By adopting the technical scheme, the turning threshold is 25 degrees instead of other degrees, so that the turning state can be judged more accurately.
As a further improvement of the present invention, step S4 includes the following steps,
s41, calculating the average foot displacement gradient of the data in the cluster:
in the formula (I), the compound is shown in the specification,
to be the average foot displacement gradient,
in order to average out the vertical displacement of the foot,
mean foot horizontal displacement;
s42, comparing the average foot displacement gradient with a stair ascending threshold value, a stair descending threshold value, an ascending threshold value and a descending threshold value, identifying all gait cycles in the cluster to be in a stair ascending state if the average foot displacement gradient is larger than the stair ascending threshold value, identifying all gait cycles in the cluster to be in an ascending state if the average foot displacement gradient is smaller than the stair ascending threshold value and larger than the ascending threshold value, identifying all gait cycles in the cluster to be in a flat walking state if the average foot displacement gradient is smaller than the ascending threshold value and larger than the descending threshold value, identifying all gait cycles in the cluster to be in a descending state if the average foot displacement gradient is smaller than the descending threshold value, and identifying all gait cycles in the cluster to be in a descending state if the average foot displacement gradient is smaller than the descending threshold value. By adopting the technical scheme, the average foot displacement gradient is compared with each threshold value, so that on one hand, real-time state data during walking is combined, and on the other hand, the specific walking state can be accurately and efficiently judged.
As a further improvement of the invention, the threshold value for going upstairs is 0.3, the threshold value for going downstairs is-0.3, the threshold value for going uphill is 0.1, and the threshold value for going downhill is-0.1. By adopting the technical scheme, the threshold values are set to be the values, but not other values, so that the walking state can be judged more accurately.
As a further improvement of the present invention, step S3 further includes adjusting parameters of the clustering algorithm so that the radius of the formed cluster does not exceed 0.1 meter.
As a further improvement of the invention, the clustering algorithm is a density-based DBSCAN algorithm.
The wearable device identifies the walking state by adopting the human body walking state identification method for the wearable device according to any one of the above aspects, the wearable device comprises an inertial sensor unit which is wearable on a user's shank and is close to an ankle joint, the inertial sensor unit comprises an inertial measurement sensor module and a single chip microcomputer, the inertial measurement sensor module comprises a three-dimensional accelerometer and a three-dimensional angular velocity meter, and the single chip microcomputer is connected with the inertial measurement sensor module and calculates the horizontal displacement, the vertical displacement and the steering angle of the foot according to the acceleration and the angular velocity measured by the inertial measurement sensor module.
As a further improvement of the present invention, the inertial measurement sensor module is an inertial measurement sensor module based on an MPU6050 chip.
As a further improvement of the invention, the sampling frequency of the inertial measurement sensor module is not lower than 100 Hz.
The technical features of the above-described preferred embodiments may be combined with each other without conflicting ones, and are not limited thereto.
Compared with the prior art, the invention has the beneficial effects that:
(1) the walking state of the human body is identified by using the invention, which is not limited by the field and is easy to popularize;
(2) the walking state is identified by using the horizontal displacement, the vertical displacement and the steering angle of the foot which are directly related to the walking state as characteristics, so that the walking state has better precision;
(3) the wearable device is used for identifying the walking state, and the wearable device has good application value and wide application range.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
FIG. 1 is a schematic diagram of horizontal and vertical displacement of a foot according to the present invention;
FIG. 2 is a schematic view of the steering angle of the foot according to the present invention;
FIG. 3 is another schematic view of the foot steering angle of the present invention;
fig. 4 is a schematic view of a wearable device according to the present invention;
in the figure: 1 is an inertial sensor unit; 2 is foot, H is foot horizontal displacement, V is foot vertical displacement; delta theta is the foot steering angle thetaEIs the heading angle of the foot at the end of the gait cycle, θSIs the heading angle of the foot at the beginning of the gait cycle.
Detailed Description
To further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description of the preferred embodiments, structures, features and effects according to the present invention will be provided in the accompanying drawings.
Referring to fig. 1 to 4, the present invention recognizes a walking state of a user using a wearable device including an inertial sensor unit. In one embodiment, the human body walking state identification method for the wearable device provided by the invention comprises the following steps:
s1, measuring horizontal displacement, vertical displacement and steering angle of a foot in each gait cycle in a walking process of a user through wearable equipment;
s2, identifying the turning and walking state of the user according to the steering angle;
s3, clustering the horizontal displacement and the vertical displacement of the feet of each step of the user through a clustering algorithm to form different clusters; the same cluster comprises both horizontal displacement data and vertical displacement data;
and S4, identifying the walking state of the cluster according to the average value of the horizontal displacement and the vertical displacement in the cluster, including walking on the flat ground, ascending the stairs, descending the stairs, ascending the slope and descending the slope.
Taking a certain user as an example, the specific implementation process of the invention is as follows:
(1) preparation work:
in this embodiment, as shown in fig. 4, the wearable device includes an inertial sensor unit 1. The specific models of each sensor and other electronic elements can be selected according to actual needs. The inertial sensor unit comprises an inertial measurement sensor module based on an MPU6050 chip, the inertial measurement sensor module comprises a three-dimensional accelerometer and a three-dimensional gyroscope (a three-dimensional angular velocity meter) and is used for acquiring three-dimensional acceleration and three-dimensional angular velocity data in the walking process of a user, and the sampling frequency is 100 Hz. The sensor is placed on the outside of the user's right calf near the ankle using an elastic securing strap, as shown in fig. 4. The device also comprises a single chip microcomputer which is used for calculating the acceleration and angular velocity data collected by the sensor to obtain the horizontal displacement, the vertical displacement and the steering angle of the foot.
The horizontal, vertical displacement of the foot is the displacement of the foot in the horizontal, vertical direction after going through a full gait cycle, as shown in fig. 1. The gait cycle refers to the cycle of walking, taking the same foot as an example, the flat-foot stage (the surface of the foot is in full contact with the ground) is regarded as the beginning of the gait cycle, and then the foot lifts off the ground, steps forward, falls to the ground, and reaches the next flat-foot stage, which is regarded as the end of the gait cycle.
The foot heading angle is the orientation of the foot in the horizontal plane, and the foot steering angle is the change value of the heading angle of the foot after the foot goes through a whole gait cycle, as shown in fig. 2. More specifically, as shown in FIG. 3, the heading angle refers to the angle between the orientation of the foot and a transverse reference line, which is positive above the transverse reference line and negative below the transverse reference line. ThetaEIs the heading angle of the foot at the end of the gait cycle, θSIs the heading angle of the foot at the beginning of the gait cycle.
A user walks on a flat ground, and a single chip microcomputer in the device calculates acceleration and angular velocity data collected by a sensor to obtain and store horizontal displacement, vertical displacement and steering angle of the foot.
(2) Human walking state identification:
after the preparation work is finished, the walking state of the user can be identified.
In step S2, the turning travel state identification process includes the steps of:
s21, calculating a steering angle of the foot from the beginning of the gait cycle to the end of the gait cycle:
Δθ＝|θE-θS|
in the formula: delta theta is a steering angle thetaEIs the heading angle of the foot at the end of the gait cycle, θSIs the heading angle of the foot at the beginning of the gait cycle;
s22, comparing the steering angle with a turning threshold value, and identifying the steering angle as a turning walking state if the steering angle is larger than the turning threshold value; in the present embodiment, the turning threshold is 25 °.
Clustering the residual data according to the characteristics of the horizontal displacement and the vertical displacement of the feet by using a DBSCAN clustering algorithm:
(1) detecting an object p which is not checked in the database, if the object p is not processed (not classified as a certain cluster or marked as noise), checking the neighborhood (the area with the distance p smaller than the radius of the neighborhood), if the number of included objects is not smaller than minPts (minimum number), establishing a new cluster C, and adding all points in the new cluster C into a candidate set N;
(2) checking the neighborhood of all unprocessed objects q in the candidate set N, and adding the objects q to the candidate set N if at least minPts objects are contained; if q does not belong to any cluster, adding q to C;
(3) repeating the step (2), and continuously checking the unprocessed objects in the N, wherein the current candidate set N is empty;
(4) repeating steps (1) to (3) until all objects fall into a certain cluster or are marked as noise.
Step S3 further comprises adjusting minPts parameter and neighborhood radius of the clustering algorithm to make the radius of the formed cluster not exceed 0.1 m; in this embodiment minPts is 10 and the neighborhood radius is 0.03 meters.
In step S4, the method includes the steps of,
s41, calculating the average foot displacement gradient of the data in the cluster:
in the formula (I), the compound is shown in the specification,
to be the average foot displacement gradient,
in order to average out the vertical displacement of the foot,
mean foot horizontal displacement;
s42, comparing the average foot displacement gradient with a stair ascending threshold value, a stair descending threshold value, an ascending threshold value and a descending threshold value, identifying all gait cycles in the cluster to be in a stair ascending state if the average foot displacement gradient is larger than the stair ascending threshold value, identifying all gait cycles in the cluster to be in an ascending state if the average foot displacement gradient is smaller than the stair ascending threshold value and larger than the ascending threshold value, identifying all gait cycles in the cluster to be in a flat walking state if the average foot displacement gradient is smaller than the ascending threshold value and larger than the descending threshold value, identifying all gait cycles in the cluster to be in a descending state if the average foot displacement gradient is smaller than the descending threshold value, and identifying all gait cycles in the cluster to be in a descending state if the average foot displacement gradient is smaller than the descending threshold value.
In this embodiment, the threshold for going upstairs is 0.3, the threshold for going downstairs is-0.3, the threshold for going uphill is 0.1, and the threshold for going downhill is-0.1.
(4) The walking state comprehensive index measurement effect is as follows:
in this example, the user walks 80 steps (80 gait cycles) in a common plane, and 20 steps each for ascending stairs, descending stairs, ascending slopes, descending slopes, and turning, taking the wearable sensor-worn foot as an example, in the preparation process. And (3) generating 7 clusters in total by using a clustering algorithm, wherein each cluster is used for ascending stairs, descending stairs, ascending slopes and descending slopes, and 3 clusters are walked on the flat ground (for example, three different flat ground walking speeds are detected). The identification rate of each walking state reaches more than 90 percent. Compared with the prior art, the device and the method can realize accurate identification of the walking state of the user.
The above-mentioned embodiments are only some preferred embodiments of the present invention, but not intended to limit the present invention. Various changes and modifications may be made by one of ordinary skill in the pertinent art without departing from the spirit and scope of the present invention. For example, the above embodiments may also use other algorithms or use other sensors to calculate the horizontal displacement, vertical displacement, steering angle of the foot in real time, such as millimeter wave radar, infrared sensors, laser radar, etc. The wearable device may be modified in other configurations or ways known in the art, such as using another inertial sensor chip, using a higher sampling frequency, etc.
Although the present invention has been described with reference to the preferred embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, but is intended to cover various modifications, equivalents and alternatives falling within the spirit and scope of the invention.
Claims (4)
1. A human body walking state identification method for a wearable device is characterized by comprising the following steps:
s1, measuring horizontal displacement, vertical displacement and steering angle of a foot in each gait cycle in a walking process of a user through wearable equipment;
s2, identifying the turning and walking state of the user according to the steering angle;
s3, clustering the horizontal displacement and the vertical displacement of the feet of each step of the user through a clustering algorithm to form different clusters;
s4, identifying the walking state of the cluster according to the average value of horizontal displacement and vertical displacement in the cluster, including walking on the flat ground, ascending stairs, descending stairs, ascending slopes and descending slopes; the turning and walking state identification process comprises the following steps:
s21, calculating a steering angle of the foot from the beginning of the gait cycle to the end of the gait cycle:
Δθ＝|θE-θS|
in the formula: delta theta is a steering angle thetaEIs the heading angle of the foot at the end of the gait cycle, θSIs the heading angle of the foot at the beginning of the gait cycle;
s22, comparing the steering angle with a turning threshold value, and identifying the steering angle as a turning walking state if the steering angle is larger than the turning threshold value;
in step S1, the vertical displacement refers to a displacement of the foot in the flat-foot phase relative to the vertical direction in the flat-foot phase in the previous gait cycle after the foot has undergone a full gait cycle;
in step S4, the method includes the steps of,
s41, calculating the average foot displacement gradient of the data in the cluster:
in the formula (I), the compound is shown in the specification,
to be the average foot displacement gradient,
in order to average out the vertical displacement of the foot,
mean foot horizontal displacement;
s42, comparing the average foot displacement gradient with a stair ascending threshold value, a stair descending threshold value, an ascending threshold value and a descending threshold value, identifying all gait cycles in the cluster to be in a stair ascending state if the average foot displacement gradient is larger than the stair ascending threshold value, identifying all gait cycles in the cluster to be in an ascending state if the average foot displacement gradient is smaller than the stair ascending threshold value and larger than the ascending threshold value, identifying all gait cycles in the cluster to be in a flat ground walking state if the average foot displacement gradient is smaller than the ascending threshold value and larger than the descending threshold value, identifying all gait cycles in the cluster to be in a descending state if the average foot displacement gradient is smaller than the descending threshold value, and identifying all gait cycles in the cluster to be in a descending state if the average foot displacement gradient;
the turning threshold is 25 degrees; the threshold value of going upstairs is 0.3, the threshold value of going downstairs is-0.3, the threshold value of going uphill is 0.1, and the threshold value of going downhill is-0.1;
step S3 further comprises adjusting parameters of the clustering algorithm to make the radius of the formed cluster not more than 0.1 m;
the clustering algorithm is a DBSCAN algorithm based on density; the method comprises the following steps:
(1) detecting an object p which is not checked in a database, if the p is not classified as a certain cluster or marked as noise, checking the neighborhood of the p, if the number of included objects is not less than the minimum number, establishing a new cluster C, and adding all points in the new cluster C into a candidate set N;
(2) checking the neighborhood of all the unprocessed objects q in the candidate set N, and adding the objects to N if at least the minimum number of the objects is contained; if q does not belong to any cluster, adding q to C;
(3) repeating the step (2), and continuously checking the unprocessed objects in the N, wherein the current candidate set N is empty;
(4) repeating steps (1) to (3) until all objects fall into a certain cluster or are marked as noise.
2. A wearable device for recognizing a walking state of a human body according to the method for recognizing a walking state of a wearable device of claim 1, wherein the wearable device comprises an inertial sensor unit wearable on a lower leg of a user near an ankle joint, the inertial sensor unit comprises an inertial measurement sensor module and a single chip, the inertial measurement sensor module comprises a three-dimensional accelerometer and a three-dimensional angular velocity meter, and the single chip is connected to the inertial measurement sensor module and calculates a horizontal displacement, a vertical displacement and a steering angle of the foot according to an acceleration and an angular velocity measured by the inertial measurement sensor module.
3. The wearable device according to claim 2, wherein the inertial measurement sensor module is an MPU6050 chip-based inertial measurement sensor module.
4. The wearable device according to claim 2, wherein the sampling frequency of the inertial measurement sensor module is not lower than 100 Hz.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911368933.5A CN111000567B (en) | 2019-12-26 | 2019-12-26 | Human body walking state identification method for wearable device and wearable device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911368933.5A CN111000567B (en) | 2019-12-26 | 2019-12-26 | Human body walking state identification method for wearable device and wearable device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111000567A CN111000567A (en) | 2020-04-14 |
| CN111000567B true CN111000567B (en) | 2021-07-20 |
Family
ID=70118207
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911368933.5A Active CN111000567B (en) | 2019-12-26 | 2019-12-26 | Human body walking state identification method for wearable device and wearable device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111000567B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1066793A2 (en) * | 1999-07-06 | 2001-01-10 | Dynastream Inc. | Motion analysis system |
| CN104296750A (en) * | 2014-06-27 | 2015-01-21 | 大连理工大学 | Zero speed detecting method, zero speed detecting device, and pedestrian navigation method as well as pedestrian navigation system |
| CN104635732A (en) * | 2013-11-08 | 2015-05-20 | 三星电子株式会社 | Walk-assistive robot and method of controlling the same |
| CN104983489A (en) * | 2015-07-28 | 2015-10-21 | 河北工业大学 | Road condition identifying method for lower limb prosthesis walking |
| CN107330249A (en) * | 2017-06-09 | 2017-11-07 | 常州大学 | A kind of Parkinsonian symptoms area of computer aided method of discrimination based on KINECT skeleton datas |
| EP3257437A1 (en) * | 2016-06-13 | 2017-12-20 | Friedrich-Alexander-Universität Erlangen-Nürnberg | Method and system for analyzing human gait |
| CN107784318A (en) * | 2017-09-12 | 2018-03-09 | 天津大学 | The learning method that a kind of robustness similar diagram for being applied to various visual angles cluster represents |
| CN108073861A (en) * | 2016-11-16 | 2018-05-25 | 东北大学秦皇岛分校 | A kind of new abnormal gait analysis method and system |
| CN109760015A (en) * | 2017-11-10 | 2019-05-17 | 三星电子株式会社 | Control method and control equipment for walking of turning |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105769209A (en) * | 2016-03-31 | 2016-07-20 | 联想(北京)有限公司 | Method for calculating heat consumption and electronic device |
-
2019
- 2019-12-26 CN CN201911368933.5A patent/CN111000567B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1066793A2 (en) * | 1999-07-06 | 2001-01-10 | Dynastream Inc. | Motion analysis system |
| CN104635732A (en) * | 2013-11-08 | 2015-05-20 | 三星电子株式会社 | Walk-assistive robot and method of controlling the same |
| CN104296750A (en) * | 2014-06-27 | 2015-01-21 | 大连理工大学 | Zero speed detecting method, zero speed detecting device, and pedestrian navigation method as well as pedestrian navigation system |
| CN104983489A (en) * | 2015-07-28 | 2015-10-21 | 河北工业大学 | Road condition identifying method for lower limb prosthesis walking |
| EP3257437A1 (en) * | 2016-06-13 | 2017-12-20 | Friedrich-Alexander-Universität Erlangen-Nürnberg | Method and system for analyzing human gait |
| CN108073861A (en) * | 2016-11-16 | 2018-05-25 | 东北大学秦皇岛分校 | A kind of new abnormal gait analysis method and system |
| CN107330249A (en) * | 2017-06-09 | 2017-11-07 | 常州大学 | A kind of Parkinsonian symptoms area of computer aided method of discrimination based on KINECT skeleton datas |
| CN107784318A (en) * | 2017-09-12 | 2018-03-09 | 天津大学 | The learning method that a kind of robustness similar diagram for being applied to various visual angles cluster represents |
| CN109760015A (en) * | 2017-11-10 | 2019-05-17 | 三星电子株式会社 | Control method and control equipment for walking of turning |
Non-Patent Citations (1)
| Title |
|---|
| Mixture-Model Clustering of Pathological Gait Patterns;Elham Dolatabadi et al;《IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS》;20170930;第21卷(第5期);第1297-1305页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111000567A (en) | 2020-04-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mannini et al. | Walking speed estimation using foot-mounted inertial sensors: Comparing machine learning and strap-down integration methods | |
| CN104323780B (en) | Pedestrian's gait classification system and method based on support vector machine | |
| CN104075730B (en) | Gait counting method and gait counter | |
| Cho et al. | Autogait: A mobile platform that accurately estimates the distance walked | |
| CN106767888A (en) | A kind of meter based on Wave crest and wave trough detection walks algorithm | |
| CN106705968A (en) | Indoor inertial navigation algorithm based on posture recognition and step length model | |
| CN108537101B (en) | Pedestrian positioning method based on state recognition | |
| KR102107379B1 (en) | Method for Prediction Frailty Using Triple Axis Motion Meter, Prediction Frailty System using Triple Axis Motion Meter and Wearable Prediction Frailty Device | |
| CN105992932A (en) | Improvements in the detection of walking in measurements of the movement of a user | |
| CN105877757A (en) | Multi-sensor integrated human motion posture capturing and recognizing device | |
| CN108844533A (en) | A kind of free posture PDR localization method based on Multi-sensor Fusion and attitude algorithm | |
| US20140330535A1 (en) | Method and apparatus for elevator motion detection | |
| CN108334827B (en) | Gait identity authentication method based on intelligent shoe and intelligent shoe | |
| CN103411607A (en) | Method for pedestrian step size estimation and dead reckoning | |
| EP2951533A1 (en) | Method and system for varying step length estimation using nonlinear system identification | |
| CN107958221A (en) | A kind of human motion Approach for Gait Classification based on convolutional neural networks | |
| CN103425895A (en) | Multi-sensor motion and posture monitoring and analyzing method and system | |
| CN109646009B (en) | Gait space-time parameter calculation method based on portable gait analysis system | |
| CN110313918A (en) | A kind of gait phase recognition methods and system based on plantar pressure | |
| CN110974242B (en) | Gait abnormal degree evaluation method for wearable device and wearable device | |
| CN114469073B (en) | Gait analysis and abnormality detection method based on wearable sensor | |
| CN109528212A (en) | A kind of abnormal gait identification device and method | |
| WO2020040465A1 (en) | Method for providing stair-walking measuring service using altitude and direction | |
| WO2019047410A1 (en) | Method and apparatus for counting the number of steps | |
| KR101674816B1 (en) | Device and method for gait pattern analysis with imu |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 310052 room 228, 2 / F, building 1, no.1180 Bin'an Road, Binjiang District, Hangzhou City, Zhejiang Province Applicant after: Zhejiang wellbeing Technology Co.,Ltd. Address before: 310052 room 228, 2 / F, building 1, no.1180 Bin'an Road, Binjiang District, Hangzhou City, Zhejiang Province Applicant before: Zhejiang Welfare Medical Devices Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |