CN114550099A - Comprehensive health management system based on digital twins - Google Patents
Comprehensive health management system based on digital twins Download PDFInfo
- Publication number
- CN114550099A CN114550099A CN202210194330.3A CN202210194330A CN114550099A CN 114550099 A CN114550099 A CN 114550099A CN 202210194330 A CN202210194330 A CN 202210194330A CN 114550099 A CN114550099 A CN 114550099A
- Authority
- CN
- China
- Prior art keywords
- sitting posture
- change
- posture
- similarity
- current
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Abstract
The invention relates to the field of sitting postures, in particular to a comprehensive health management system based on digital twins, which comprises: the sitting posture inclination degree acquisition module is used for acquiring the inclination degree of the current sitting posture of the human body; the sitting posture change amplitude acquisition module is used for acquiring the change amplitude of the current sitting posture compared with the standard sitting posture; the similarity evaluation module is used for calculating the similarity between the current sitting posture and the standard sitting posture based on the inclination degree, the change amplitude and the position change of the eye-shoulder key points in the change process; the similarity correction module is used for determining a correction coefficient according to the current sitting posture and correcting the similarity by using the correction coefficient; the adjustment prompting module is used for judging whether a prompt of sitting posture adjustment is needed or not according to the corrected similarity; and the digital twinning module is used for constructing a virtual human body model based on a digital twinning technology and updating the sitting posture of the virtual human body model according to the real-time monitored data. The invention can reduce the times of error reminding.
Description
Technical Field
The invention relates to the field of sitting posture monitoring, in particular to a comprehensive health management system based on digital twins.
Background
The healthy sitting posture can help people to improve the working efficiency, relieve the pressure of the spine and is beneficial to the bone health, and the poor sitting posture is one of the important reasons of spinal diseases such as soreness and backache, scoliosis, lumbar disc herniation and the like of people. The traditional healthy sitting posture curing method forcibly corrects the wrong sitting posture of people by limiting the moving range of a human body through the physical stretching effect of a bandage, but the correction method can cause irreversible damage to the body and has weak correction effect. Therefore, the chair helps guide people to develop good sitting habits, and is the most effective way for preventing the problems of spinal diseases. The existing guiding mode is that sitting posture detection is firstly carried out, and when the sitting posture is detected to be out of standard, relevant prompt is carried out, so that people keep the correct sitting posture. However, most of the existing methods judge whether the human body sitting posture is standard or not based on the data change of the seat surface pressure sensor, and the detection result has large errors.
Disclosure of Invention
In order to solve the above technical problems, the present invention aims to provide a comprehensive health management system based on digital twin, and the adopted technical scheme is as follows:
one embodiment of the present invention provides a digital twin-based integrated health management system, which includes:
the sitting posture inclination degree acquisition module is used for acquiring the inclination degree of the current sitting posture of the human body;
the sitting posture change amplitude acquisition module is used for acquiring the change amplitude of the current sitting posture compared with the standard sitting posture based on the pressure change data and the included angle between the human eyes and the display; the pressure is the pressure of a human body on the seat;
the similarity evaluation module is used for calculating the similarity between the current sitting posture and the standard sitting posture based on the inclination degree and the change amplitude of the current sitting posture and the position change of the eye-shoulder key points in the change process;
the similarity correction module is used for determining a correction coefficient according to whether the human body posture corresponding to the current sitting posture is an accidental posture or not and correcting the similarity by using the correction coefficient; the accidental posture is a posture corresponding to accidental actions, and the accidental actions comprise bending down and turning;
the adjustment prompting module is used for judging whether a prompt of sitting posture adjustment is needed or not according to the corrected similarity;
the digital twinning module is used for constructing a virtual human body model based on a digital twinning technology and updating the sitting posture of the virtual human body model according to the data monitored in real time; the real-time monitoring data comprises pressure data and included angle data.
Further, the inclination degree of the current sitting posture of the human body is obtained, and the method specifically comprises the following steps:
and calculating a coordinate ratio according to the coordinates of key points of the left shoulder and the right shoulder, and acquiring the inclination degree of the current sitting posture of the human body.
Further, after the posture change is finished, the pressure sensing points with the changed values are change sensing points, pressure data of the change sensing points are obtained, and the pressure change rate of each change sensing point is calculated by comparing the pressure data of each change sensing point corresponding to the standard sitting posture; the rate of pressure change is pressure change data.
Further, the obtaining of the variation range of the current sitting posture specifically includes:
calculating the difference value between the maximum value and the minimum value of the pressure change rate, and calculating the change amplitude of the current sitting posture according to the difference value and the included angle between the human eyes and the display; the larger the difference value is, the larger the change amplitude of the current sitting posture is, the larger the included angle between the human eyes and the display is, and the larger the change amplitude of the current sitting posture is.
Further, based on the inclination degree and the variation range of the current sitting posture and the position variation of the eye-shoulder key points in the variation process, the similarity between the current sitting posture and the standard sitting posture is calculated, and the method specifically comprises the following steps:
acquiring a coordinate difference sequence of both eyes and a coordinate difference sequence of both shoulders in the posture change process; respectively calculating the position similarity of the eye key points and the shoulder key points of the current sitting posture and the standard sitting posture by combining the coordinate difference sequence of the eyes and the coordinate difference sequence of the shoulders under the standard sitting posture;
and calculating the similarity between the current sitting posture and the standard sitting posture according to the inclination degree, the variation amplitude, the eye key point position similarity and the shoulder key point similarity of the current sitting posture.
Furthermore, the corresponding correction coefficient when the human posture corresponding to the current sitting posture is an accidental posture is smaller than the corresponding correction coefficient when the human posture corresponding to the current sitting posture is a non-accidental posture.
Further, the human body is subjected to image acquisition, and eye-shoulder key points are extracted based on the acquired images.
The embodiment of the invention at least has the following beneficial effects: the sitting posture monitoring device is used for monitoring the sitting posture, the monitoring result is high in precision, and when the sitting posture is abnormal, the device can remind people in time, so that people can be guided to form a good sitting posture habit; in addition, the invention can avoid the interference of accidental sitting postures such as bending over, turning over and the like corresponding to the sitting postures, and does not prompt when the sitting postures appear, thereby achieving the effect of only prompting the non-standard sitting postures and reducing the times of wrong prompting.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a block diagram of an embodiment of the system of the present invention.
Detailed Description
To further illustrate the technical means and effects of the present invention for achieving the predetermined objects, the following description, in conjunction with the accompanying drawings and preferred embodiments, describes a digital twin-based integrated health management system according to the present invention, and further describes the detailed implementation, structure, features and effects thereof. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following application scenarios are taken as examples to illustrate the present invention:
the application scene is as follows: an office scene, specifically, a person sits on a seat to work; arranging a camera/visual sensor on a display (computer screen), wherein the camera is used for collecting images of people and processing the collected images to obtain an included angle between human eyes and the display; the seat surface of the embodiment is provided with a pressure sensor, preferably, the seat armrest is also provided with the pressure sensor, and the embodiment adopts a piezoresistive film pressure sensor which is provided with a plurality of pressure sensing points; in this embodiment, the pressure sensors are uniformly distributed on the chair in a matrix mode, and the whole cushion area, the armrest areas on the left side and the right side, and the backrest are fully paved, so that the change of the sitting posture of the human body can be sensed based on the information brought back by the pressure sensors no matter the human body moves to any place of the chair.
The following describes a specific scheme of the digital twin-based integrated health management system in detail with reference to the accompanying drawings.
Referring to fig. 1, there is shown a block diagram of a digital twin-based integrated health management system according to an embodiment of the present invention, the system including:
the sitting posture inclination degree acquisition module is used for acquiring the inclination degree of the current sitting posture of the human body;
the sitting posture change amplitude acquisition module is used for acquiring the change amplitude of the current sitting posture compared with the standard sitting posture based on the pressure change data and the included angle between the human eyes and the display; the pressure is the pressure of a human body on the seat;
the similarity evaluation module is used for calculating the similarity between the current sitting posture and the standard sitting posture based on the inclination degree and the change amplitude of the current sitting posture and the position change of the eye-shoulder key points in the change process;
the similarity correction module is used for determining a correction coefficient according to whether the human body posture corresponding to the current sitting posture is an accidental posture or not and correcting the similarity by using the correction coefficient; the accidental posture is a posture corresponding to accidental actions, and the accidental actions comprise bending down and turning;
the adjustment prompting module is used for judging whether a prompt of sitting posture adjustment is needed or not according to the corrected similarity;
the digital twinning module is used for constructing a virtual human body model based on a digital twinning technology and updating the sitting posture of the virtual human body model according to the real-time monitoring data; the real-time monitoring data comprises pressure data and included angle data.
The following takes the change from the previous sitting posture to the current sitting posture as an example, and each module above is described in detail:
and the sitting posture inclination degree acquisition module is used for acquiring the inclination degree of the current sitting posture of the human body.
Calculating a coordinate ratio according to the coordinates of key points of the left shoulder and the right shoulder, and acquiring the inclination degree of the current sitting posture of the human body; preferably, according to the height coordinates (vertical coordinates) of key points of the left shoulder and the right shoulder, calculating a coordinate ratio to obtain the inclination degree of the current sitting posture of the human body: the posture change process is from the previous sitting posture to the current sitting posture, so that the coordinates of key points of the left shoulder and the right shoulder of a person in the change process are obtained, the coordinates are represented by (x, y), x represents the horizontal position of the key points of the shoulders, y represents the vertical position of the key points of the shoulders, a left shoulder key point coordinate sequence and a right shoulder key point coordinate sequence are obtained, and a left shoulder key point coordinate y mean value and a right shoulder key point y mean value are obtained based on the left shoulder key point coordinate sequence and the right shoulder key point coordinate sequence; calculating a coordinate ratio, specifically, calculating a ratio phi of a y-mean value of the left shoulder key point coordinates and a y-mean value of the right shoulder key point coordinates; or calculating the ratio phi of the y-mean value of the right shoulder key point coordinates to the y-mean value of the left shoulder key point coordinates; and acquiring the inclination degree of the current sitting posture according to the ratio phi, preferably, as an example, the absolute value of the difference between the ratio phi and 1, namely | phi-1 | is the inclination degree of the current sitting posture, and the larger the absolute value of the difference between the ratio phi and 1 is, the more inclined the current sitting posture is.
The sitting posture change amplitude acquisition module is used for acquiring the change amplitude of the current sitting posture compared with the standard sitting posture based on the pressure change data and the included angle between the human eyes and the display; the pressure is the pressure of a human body on the seat.
After the posture change is finished, the pressure sensing points with the changed numerical values are change sensing points, pressure data of the change sensing points are obtained, and the pressure change rate of each change sensing point is calculated compared with the pressure data of each change sensing point corresponding to the standard sitting posture; the rate of pressure change is pressure change data. As an example, the calculation of the pressure change rate of each change sensing point is specifically:
c is the pressure change rate of a change induction point, P is the pressure data of the change induction point in the current sitting posture, PSign boardThe pressure data of the change sensing point under the standard sitting posture is obtained.
In one embodiment, an included angle between a human eye and a display is obtained by using a camera/vision sensor and an angle sensor, the camera/vision sensor correspondingly senses the position of the human eye, and the angle sensor measures the angle between the human eye at the position and a screen to obtain an included angle value alpha.
In another embodiment, a camera/vision sensor is used for acquiring images of people to obtain images of the people, two-dimensional image coordinates of key points of human eyes are obtained based on the images of the people, three-dimensional image coordinates of the key points of human eyes in an actual space are obtained according to the two-dimensional image coordinates of the key points of human eyes, and specifically, the process of obtaining the three-dimensional coordinates based on the two-dimensional coordinates is prior and is not repeated; the method comprises the steps of acquiring three-dimensional coordinates of a display in a practical space, preferably, acquiring the three-dimensional coordinates of a center point of the display, and calculating an angle alpha between human eyes and a screen based on the three-dimensional coordinates of the display and the three-dimensional coordinates of key points of the human eyes. It should be noted that the angle between the human eyes and the screen may be calculated based on the three-dimensional coordinates of the key points of the left eye and the right eye, or may be calculated based on the three-dimensional coordinates of the central point of the line connecting the key points of the left eye and the right eye.
Based on pressure change data and the included angle between human eyes and the display, obtain compare with standard position of sitting, the range of change of present position of sitting, specifically: calculating the difference value between the maximum value and the minimum value of the pressure change rate, and calculating the change amplitude of the current sitting posture according to the difference value and the included angle between the human eyes and the display; the larger the difference value is, the larger the change amplitude of the current sitting posture is, the larger the included angle between the human eyes and the display is, and the larger the change amplitude of the current sitting posture is. As an example, the magnitude of change in the current sitting posture is calculated as:
u represents the change amplitude of the current sitting posture, and the smaller the U value is, the larger the change amplitude of the current sitting posture is compared with the standard sitting posture; cMAXAnd CMINRespectively the maximum and minimum values of the rate of change of pressure at each change induction point, CMAX-CMINThe larger the value, the more uneven the stress, and the larger the change width, and use
Normalizing the sitting posture data, wherein the smaller the normalized value is, the larger the variation amplitude of the current sitting posture is compared with the standard sitting posture; alpha is the angle between the human eye and the display, using e-αNormalizing it, e-αThe smaller the value, the larger the magnitude of the change in the current sitting posture compared to the standard sitting posture is considered.
And the similarity evaluation module is used for calculating the similarity between the current sitting posture and the standard sitting posture based on the inclination degree and the variation amplitude of the current sitting posture and the position variation of the eye-shoulder key points in the variation process.
Specifically, in the posture change process, a coordinate difference sequence of both eyes and a coordinate difference sequence of both shoulders are obtained; respectively calculating the position similarity of the eye key points and the shoulder key points of the current sitting posture and the standard sitting posture by combining the coordinate difference sequence of the eyes and the coordinate difference sequence of the shoulders under the standard sitting posture; and calculating the similarity between the current sitting posture and the standard sitting posture according to the inclination degree, the variation amplitude, the eye key point position similarity and the shoulder key point similarity of the current sitting posture. As an example, the similarity between the current sitting posture and the standard sitting posture is calculated as follows:
r represents the similarity between the current sitting posture and the standard sitting posture, and the larger the R value is, the more similar the current sitting posture and the standard sitting posture is; e is the coordinate difference sequence of the two eyes in the current sitting posture, ESign boardThe coordinate difference sequence of the key points of the eyes is the same as the key points of the shoulders in the standard sitting posture, the image coordinates of the key points of the eyes are expressed as (x, y), and the coordinate difference sequence of the key points of the eyes can be obtained based on the x coordinate or the y coordinate; s is a coordinate difference sequence of shoulders in the current sitting postureSign boardThe coordinate difference sequence of the shoulders in the standard sitting posture can be obtained based on the x coordinate or the y coordinate similarly; DTW is the distance between two sequences obtained based on a dynamic time normalization algorithm, and can represent the similarity between the two sequences, wherein the smaller the DTW value, the more similar the two sequences.
It is noted that the embodiment performs image acquisition on a human body, and extracts eye-shoulder key points based on the acquired image.
The similarity correction module is used for determining a correction coefficient according to whether the human body posture corresponding to the current sitting posture is an accidental posture or not and correcting the similarity by using the correction coefficient; the accidental posture is a posture corresponding to accidental actions, and the accidental actions comprise bending down and turning. Note that the incidental posture is an end posture of the incidental movement.
In one embodiment, a camera can be used for continuously acquiring images of people, whether the human body posture corresponding to the current sitting posture is accidental posture is judged based on the obtained image sequence, namely, action recognition is carried out based on the image sequence, specifically, action recognition can be carried out based on a neural network, after corresponding action is recognized, whether the action is accidental action is judged, and further whether the human body posture corresponding to the current sitting posture is accidental posture corresponding to the accidental action can be judged; acquiring a correction coefficient corresponding to the action based on a preset posture-correction coefficient corresponding relation, and further acquiring a correction coefficient corresponding to the current sitting posture; the corresponding relation of the posture and the correction coefficient is obtained by artificial setting. And the correction coefficient corresponding to the current sitting posture corresponding to the human body posture is smaller than the correction coefficient corresponding to the current sitting posture corresponding to the human body posture which is not the accidental posture. In the embodiment, when the posture of the human body corresponding to the current sitting posture is sporadic, the correction coefficient is 0.1, and when the posture of the human body corresponding to the current sitting posture is non-sporadic, the correction coefficient is 0.9.
In another embodiment, it is required to combine the pressure data of the change sensing points corresponding to the current sitting posture and the historic sitting posture to obtain a mean value of the pressure data of the change sensing points corresponding to the current sitting posture and the historic sitting posture, where the horizontal axis is the change time length from one sitting posture to another sitting posture, and the vertical axis is the mean value of the pressure data, and perform linear fitting on the mean value of the pressure data according to the sitting posture time sequence, preferably, perform linear fitting based on a least square method to obtain the change time length t from the previous sitting posture to the current sitting posture and the slope k of the corresponding straight line in the change time length, and obtain the correction coefficient corresponding to the current sitting posture according to the change time length t and the slope k, and the occurrence time of sporadic actions is relatively fast, and the mean value of the pressure data is more likely to generate sudden changes when the sporadic actions occur, so that the shorter the change time length t is, the larger the absolute value of the slope k is, the more likely that the human posture corresponding to the current sitting posture is the sporadic posture, the smaller the correction factor is; as an example, the calculation method of the correction coefficient is: m ═ e-|k|And t ', M is a correction coefficient, and t' is a value obtained by normalizing the change time duration t.
And correcting the similarity by using the correction coefficient, specifically: r′＝R*M，R′The corrected similarity.
And the adjustment prompting module is used for judging whether the prompt of sitting posture adjustment is needed according to the corrected similarity.
When R is′When the current sitting posture is less than 0.3, the posture of the human body corresponding to the current sitting posture is considered to be sporadic, and the sitting posture reminding is not carried out; when R is more than or equal to 0.3′When the sitting posture is less than 0.8, the current sitting posture is considered to be the wrong sitting posture, namely the nonstandard sitting posture, and the sitting posture reminding is carried out; when R is′When the current value is more than or equal to 0.8, the current value is consideredThe sitting posture is standard sitting posture, and the sitting posture reminding is not carried out.
The digital twinning module is used for constructing a virtual human body model based on a digital twinning technology and updating the sitting posture of the virtual human body model according to the real-time monitoring data; the real-time monitoring data comprises pressure data and included angle data.
The sitting posture of a human body is monitored in real time by a pressure sensor, a vision sensor and the like; based on real-time monitoring data, inputting the data into a twin system, describing human body sitting posture from multiple dimensions such as geometry, physics, behavior, rules and the like in a virtual space, realizing processing and fusion of multi-dimensional data, and integrating a high-fidelity virtual model of a human body; the human body and the virtual model run synchronously, so that personnel can see the current sitting posture clearly, and intelligent health management of the sitting posture of the human body is realized under the drive of twin data and the virtual model, so as to ensure that the human body keeps a good sitting posture.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And that specific embodiments have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (7)
1. A digital twinning-based integrated health management system, comprising:
the sitting posture inclination degree acquisition module is used for acquiring the inclination degree of the current sitting posture of the human body;
the sitting posture change amplitude acquisition module is used for acquiring the change amplitude of the current sitting posture compared with the standard sitting posture based on the pressure change data and the included angle between the human eyes and the display; the pressure is the pressure of a human body on the seat;
the similarity evaluation module is used for calculating the similarity between the current sitting posture and the standard sitting posture based on the inclination degree and the change amplitude of the current sitting posture and the position change of the eye-shoulder key points in the change process;
the similarity correction module is used for determining a correction coefficient according to whether the human body posture corresponding to the current sitting posture is an accidental posture or not and correcting the similarity by using the correction coefficient; the accidental posture is a posture corresponding to accidental actions, and the accidental actions comprise bending down and turning;
the adjustment prompting module is used for judging whether a prompt of sitting posture adjustment is needed or not according to the corrected similarity;
the digital twinning module is used for constructing a virtual human body model based on a digital twinning technology and updating the sitting posture of the virtual human body model according to the real-time monitoring data; the real-time monitoring data comprises pressure data and included angle data.
2. The system according to claim 1, wherein the inclination degree of the current sitting posture of the human body is acquired by:
and calculating a coordinate ratio according to the coordinates of key points of the left shoulder and the right shoulder, and acquiring the inclination degree of the current sitting posture of the human body.
3. The system of claim 2, wherein after the posture change is finished, the pressure sensing points with changed values are change sensing points, pressure data of the change sensing points are obtained, and the pressure change rate of each change sensing point is calculated by comparing the pressure data of each change sensing point corresponding to a standard sitting posture; the rate of pressure change is pressure change data.
4. The system of claim 3, wherein the obtaining of the amplitude of the change of the current sitting posture is specifically:
calculating the difference value between the maximum value and the minimum value of the pressure change rate, and calculating the change amplitude of the current sitting posture according to the difference value and the included angle between the human eyes and the display; the larger the difference value is, the larger the change amplitude of the current sitting posture is, the larger the included angle between the human eyes and the display is, and the larger the change amplitude of the current sitting posture is.
5. The system as claimed in claim 4, wherein the similarity between the current sitting posture and the standard sitting posture is calculated based on the inclination degree and the variation amplitude of the current sitting posture and the position variation of the eye-shoulder key points in the variation process, specifically:
acquiring a coordinate difference sequence of both eyes and a coordinate difference sequence of both shoulders in the posture change process; respectively calculating the position similarity of the eye key points and the shoulder key points of the current sitting posture and the standard sitting posture by combining the coordinate difference sequence of the eyes and the coordinate difference sequence of the shoulders under the standard sitting posture;
and calculating the similarity between the current sitting posture and the standard sitting posture according to the inclination degree, the variation amplitude, the eye key point position similarity and the shoulder key point similarity of the current sitting posture.
6. The system of claim 5, wherein the correction factor for the current sitting posture corresponding to the body posture being sporadic is less than the correction factor for the current sitting posture corresponding to the body posture being non-sporadic.
7. The system of claim 6, wherein the human body is image-captured, and the eye-shoulder key points are extracted based on the captured image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210194330.3A CN114550099A (en) | 2022-03-01 | 2022-03-01 | Comprehensive health management system based on digital twins |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210194330.3A CN114550099A (en) | 2022-03-01 | 2022-03-01 | Comprehensive health management system based on digital twins |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114550099A true CN114550099A (en) | 2022-05-27 |
Family
ID=81661683
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210194330.3A Pending CN114550099A (en) | 2022-03-01 | 2022-03-01 | Comprehensive health management system based on digital twins |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114550099A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116884083A (en) * | 2023-06-21 | 2023-10-13 | 圣奥科技股份有限公司 | Sitting posture detection method, medium and equipment based on key points of human body |
-
2022
- 2022-03-01 CN CN202210194330.3A patent/CN114550099A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116884083A (en) * | 2023-06-21 | 2023-10-13 | 圣奥科技股份有限公司 | Sitting posture detection method, medium and equipment based on key points of human body |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107169453B (en) | Sitting posture detection method based on depth sensor | |
| CN108618465B (en) | Soft and hard adjustable mattress for realizing intelligent learning and hardness adjusting system and method thereof | |
| CN112364694B (en) | Human body sitting posture identification method based on key point detection | |
| CN213423969U (en) | Intelligent seat control device based on posture recognition | |
| CN110934591B (en) | Sitting posture detection method and device | |
| CN114550099A (en) | Comprehensive health management system based on digital twins | |
| CN112232128B (en) | Eye tracking based method for identifying care needs of old disabled people | |
| CN109948435A (en) | Sitting posture prompting method and device | |
| CN111881886A (en) | Intelligent seat control method and device based on posture recognition | |
| CN111310798B (en) | Method for constructing facial bradykinesia detection model based on geometric features and texture features | |
| CN110946584A (en) | Method for recognizing human body sitting posture by using piezoresistive film pressure sensor group | |
| CN109101943A (en) | It is a kind of for detecting the machine vision method of Falls Among Old People | |
| CN110148092A (en) | The analysis method of teenager's sitting posture based on machine vision and emotional state | |
| TWI643096B (en) | Head and neck posture monitoring method | |
| CN109241822A (en) | A kind of multi-faceted method for detecting human face and system based on MTCNN | |
| CN113065532B (en) | Sitting posture geometric parameter detection method and system based on RGBD image | |
| CN114419676A (en) | Sitting posture analysis method and device based on artificial intelligence, computer equipment and medium | |
| CN113989936A (en) | Desk lamp capable of recognizing sitting posture of child and automatically correcting voice | |
| CN115127704B (en) | Sitting posture identification method based on flexible film pressure sensor | |
| CN116486430A (en) | Multi-resolution feature fusion-based multi-azimuth body posture assessment method | |
| CN114937341B (en) | Wheelchair fall risk monitoring method and system based on multidimensional force | |
| CN110879976A (en) | Adaptive intelligent eye movement data processing system and use method thereof | |
| CN113191319B (en) | Human body posture intelligent recognition method and computer equipment | |
| CN112690781A (en) | Sedentary reminding and health monitoring system based on multiple sensors | |
| CN116758519A (en) | Automobile seat fine adjustment method based on visual artificial intelligence AI and related equipment |
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 |