CN111160165B - Self-adaptive posture error correction detection method and device - Google Patents
Self-adaptive posture error correction detection method and device Download PDFInfo
- Publication number
- CN111160165B CN111160165B CN201911310507.6A CN201911310507A CN111160165B CN 111160165 B CN111160165 B CN 111160165B CN 201911310507 A CN201911310507 A CN 201911310507A CN 111160165 B CN111160165 B CN 111160165B
- Authority
- CN
- China
- Prior art keywords
- gesture
- detection
- posture
- adaptive
- error correction
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 137
- 238000012937 correction Methods 0.000 title claims abstract description 37
- 230000002159 abnormal effect Effects 0.000 claims abstract description 4
- 210000003128 head Anatomy 0.000 claims description 27
- 230000003044 adaptive effect Effects 0.000 claims description 24
- 238000012549 training Methods 0.000 claims description 13
- 238000004891 communication Methods 0.000 claims description 11
- 238000013145 classification model Methods 0.000 claims description 9
- 238000012423 maintenance Methods 0.000 claims description 6
- 230000003993 interaction Effects 0.000 claims description 5
- 230000036541 health Effects 0.000 claims description 4
- 239000000853 adhesive Substances 0.000 claims description 3
- 230000001070 adhesive effect Effects 0.000 claims description 3
- 230000003867 tiredness Effects 0.000 claims description 2
- 208000016255 tiredness Diseases 0.000 claims description 2
- 241000190070 Sarracenia purpurea Species 0.000 claims 1
- 238000000034 method Methods 0.000 abstract description 10
- 238000005516 engineering process Methods 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000009434 installation Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000004379 myopia Effects 0.000 description 2
- 208000001491 myopia Diseases 0.000 description 2
- 241001456553 Chanodichthys dabryi Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000004438 eyesight Effects 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000007958 sleep Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a self-adaptive posture error correction detection method and a device, wherein the method comprises the following steps: s1: fixing the position of the camera and configuring configuration information of the current gesture detection state; s2: selecting a gesture detection model according to the configuration information; s3: the camera acquires a current attitude image and detects the attitude image through a selected attitude detection model: if the gesture is detected to be abnormal, sending out an alarm, otherwise repeating the step S3, wherein the device comprises: the device comprises a shell, a fixed connecting piece, a gesture detection module, a warning module and a control module; the gesture detection module comprises a camera and a gesture judgment unit; the control module is respectively connected with the gesture judging unit and the warning module in a signal way and used for controlling the warning module to warn according to the regulation and control signal, configuring configuration information of the current gesture detection state and selecting a gesture detection model of the gesture judging unit according to the configuration information. The invention has the technical characteristics of strong self-adaptation capability, wide application range and good gesture detection performance.
Description
Technical Field
The invention belongs to the technical field of intelligent detection, and particularly relates to a self-adaptive posture error correction detection method and device.
Background
The wrong posture is easy to cause symptoms of myopia, humpback, head tilting, high and low shoulders and the like over time, and more serious diseases of cervical vertebra, lumbar vertebra, eyes and the like can be induced, and irreversible injuries are generated to the body.
The existing gesture detection technology includes a method for judging the gesture by utilizing ultrasonic ranging or infrared ranging, the problem of partial false gesture detection can be solved in the actual use process, but false detection alarm is easy to generate under the condition that other objects are shielded or the non-trunk part of the human body is shielded, specific analysis can not be conducted on the specific situation of the false gesture, and the method has a large limitation in the use process.
The other part of the technical proposal uses a rigid structure to force the user to be in a specified posture state, and the technical proposal has certain practicability in the aspect of forcing correction of the wrong posture, but limits the activity space of the person to a certain extent and causes certain inconvenience.
In addition, different crowds and different environments have certain differences in gesture detection standards, so that the limitation of the current gesture detection technology is caused, meanwhile, the use of the current gesture detection technology is limited to a specific application scene, and the detection technology cannot adapt to different application scenes, so that the practicability of the technology is greatly reduced.
Disclosure of Invention
The invention aims to provide a self-adaptive posture error correction detection method and device, which have the technical characteristics of strong self-adaptive capacity, wide application range and good posture detection performance.
In order to solve the problems, the technical scheme of the invention is as follows:
an adaptive posture error correction detection method comprises the following steps:
s1: fixing the position of the camera and configuring configuration information of the current gesture detection state;
s2: selecting a gesture detection model according to the configuration information;
s3: the camera acquires a current attitude image and detects the attitude image through a selected attitude detection model: if the gesture is detected to be abnormal, a warning is sent out, otherwise, the step S3 is repeated.
According to an embodiment of the present invention, the configuration information includes user information, usage environment information, and a gesture image library, and the following steps are further included before step S1:
a1: acquiring configuration information under different gesture detection states;
a2: and training through different configuration information to obtain a plurality of different gesture detection models.
According to an embodiment of the present invention, the gesture detection model is a classification model, and in step A2, the gesture class of the image required for training the classification model needs to be labeled.
According to an embodiment of the present invention, the gesture detection model is a regression model, and in step A2, gesture parameters need to be labeled on an image required for training the regression model.
According to an embodiment of the invention, the posture parameters include the distance of the eyes from the table top, the left and right shoulder heights, the low head angle, the swivel angle, and the offset head angle.
According to an embodiment of the present invention, in step S1, the usage environment information includes a placement position and an angle of the camera, where the placement position and the angle are configured by manual input or automatic recognition;
in step S2, the specific steps of selecting the gesture detection model according to the configuration information are as follows: and selecting a gesture detection model according to the placement position and the angle.
According to an embodiment of the present invention, the configuration of the placement position and angle by automatic recognition specifically includes the following steps:
b1: establishing a camera detection model, and collecting or inputting a standard attitude image, wherein the camera detection model is a regression model;
b2: regression is carried out on the standard attitude image through a camera detection model, so that angles of a low head, a rotating head and a deflection head are obtained;
b3: and according to the angles of the low head, the rotary head and the offset head, reversely pushing to obtain the placement position and the angle of the camera.
The invention also provides a self-adaptive posture error correction detection device, which applies the self-adaptive posture error correction detection method to detect the posture, comprising the following steps: the device comprises a shell, a fixed connecting piece arranged on the shell, and a gesture detection module, a warning module and a control module which are arranged in the shell;
the gesture detection module comprises a camera for acquiring gesture images and a gesture judging unit for detecting the gesture images and generating regulation and control signals;
the control module is respectively connected with the gesture judging unit and the warning module in a signal way and used for controlling the warning module to warn according to the regulation and control signal, configuring configuration information of the current gesture detection state and selecting a gesture detection model of the gesture judging unit according to the configuration information.
According to an embodiment of the present invention, the fixing connection member is a magnetic attraction member or a clamping member or an adhesive member or a clamping member or a locking member.
According to an embodiment of the invention, the portable desk lamp comprises a shell, a fixing connector, a support, a desk lamp, a sound, a display, a cup, a clock, a desk or a bookshelf, wherein the shell is internally fixed in the support or externally fixed on the support through the fixing connector.
According to an embodiment of the invention, the system further comprises a communication module, wherein the communication module is electrically connected with the control module and is used for feeding back the working state and the posture health report of the adaptive posture error correction detection device.
According to an embodiment of the invention, the control module is further used for counting the maintenance time of the normal posture and controlling the warning module to carry out tiredness warning according to the maintenance time.
According to an embodiment of the invention, the device further comprises a loudspeaker and a microphone for voice interaction and in signal connection with the control module, wherein the loudspeaker and the microphone are also used for acoustic ranging between the device and a user so as to assist in adjusting the fixed position of the device.
Compared with the prior art, the invention has the following advantages and positive effects:
1) The method can fix the fixed camera at any position, and adapt to the current gesture detection conditions by the gesture detection model selected by the configuration information of the current gesture detection state, particularly, before detection, a plurality of different gesture detection models are obtained by acquiring the configuration training of different gesture detection states and training in advance for selection during actual gesture detection, wherein the self-adaptation capability is improved and the application range is expanded by configuring a gesture image library, user information and using environment information for the gesture detection condition training;
2) In the method, the placing positions and angles of the cameras can be set in various ways, and as the placing positions and angles of the cameras have a great relationship with the judgment of gesture detection, different placing positions and angles correspond to different gesture detection models;
3) The device can fix the self-adaptive posture error correction detection device at any position in the environment through various fixed connecting pieces, and can be combined with any object in the environment, so that the self-adaptive capacity is improved, and the application range is expanded;
4) The device provided by the invention is convenient for human-computer interaction by arranging the loudspeaker and the microphone, has the function of acoustic ranging in the fixing process of the self-adaptive gesture error correction detection device, and can assist the installation of the device, so that the self-adaptive capacity is improved, and the application range is expanded.
Drawings
FIG. 1 is a main flow chart of an adaptive attitude error correction detection method according to the present invention;
FIG. 2 is a flow chart of automatic identification of camera placement position and angle in an adaptive gesture error correction detection method of the present invention;
fig. 3 is a schematic structural diagram of an adaptive posture error correction detecting device according to the present invention.
Reference numerals illustrate:
1-a fixed connection; 2-a communication module; 3-a housing; 4-warning buzzer; 5-a key module; 6-button; 7-right position warning lamp; 8-an error posture warning lamp; 9- -warning lamp at left position; 10-a camera; 11-a data transmission port; 12-charging interface.
Detailed Description
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following description will explain the specific embodiments of the present invention with reference to the accompanying drawings. It is evident that the drawings in the following description are only examples of the invention, from which other drawings and other embodiments can be obtained by a person skilled in the art without inventive effort.
For the sake of simplicity of the drawing, the parts relevant to the present invention are shown only schematically in the figures, which do not represent the actual structure thereof as a product. Additionally, in order to simplify the drawing for ease of understanding, components having the same structure or function in some of the drawings are shown schematically with only one of them, or only one of them is labeled. Herein, "a" means not only "only this one" but also "more than one" case.
The following describes the adaptive posture error correction detection method and device according to the present invention in further detail with reference to the accompanying drawings and specific embodiments.
Example 1
Referring to fig. 1, the application provides an adaptive posture error correction detection method, which comprises the following steps:
s1: fixing the position of the camera and configuring configuration information of the current gesture detection state;
s2: selecting a gesture detection model gesture according to the configuration information;
s3: the camera acquires a current attitude image and detects the attitude image through a selected attitude detection model: if the gesture is detected to be abnormal, a warning is sent out, otherwise, the step S3 is repeated.
The present embodiment will now be specifically described:
in step S1 of the embodiment, the fixed position of the camera has various forms, and can be specifically defined according to the placement position and angle of the camera, and the fixed position can be fixed at any place where the gesture can be shot, such as a bookshelf, a desk lamp, a wall, a ground, a clock, etc., the configuration information includes user information, service environment information and gesture image library, the service environment information can include information such as the height and inclination angle of the desk, the position and angle of the camera, the height of a chair, etc., the user information can include information such as the height, weight, sex, myopia degree, distance between eyes and nose tip of a user, distance between eyes and a desk top, height between eyes and a desk top when the user is in front of the eyes, distance between shoulders and the desk top, etc., the gesture image library can be a plurality of different specific gesture images of the user under different acquisition environments, and the configuration information can be configured in a manual input or automatic identification measurement mode, such as automatic identification measurement can be performed through technologies such as image identification, infrared ranging, acoustic ranging, etc.
Referring to fig. 1, the present embodiment provides for selecting a plurality of gesture detection models to adapt to different gesture detection states, and further includes the following steps before step S1: a1: acquiring configuration information under different gesture detection states; a2: and training through different configuration information to obtain a plurality of different gesture detection models. Specifically, in step A1, different user information, usage environment information, and configuration information of the pose image library may be collected, and in step A2, a plurality of different pose detection models may be obtained by training a deep convolutional network model with different configuration information.
The gesture detection model of the present embodiment may employ a regression model or a classification model: the gesture detection model is a classification model, and in the corresponding step A2, the gesture category of the image required by the training of the classification model is required to be marked; the gesture detection model is a regression model, and in the corresponding step A2, gesture parameters need to be marked on images required by the classification model training, preferably, the gesture parameters comprise the distance between eyes and a desktop, the height of left and right shoulders, the angle of low head, the angle of turning head, the angle of head deviation, the face position and the position of eyes and nose. The face position and the eye and nose position can be marked or not, the whole algorithm is not influenced, the regression accuracy can be improved, and a large amount of marking cost is increased.
The placement positions and angles of the cameras in the configuration information have great relations with the gesture detection, different placement positions and angles are different, certain differences exist between corresponding gesture detection models, the embodiment provides a plurality of gesture detection models for selection, and different gesture detection models correspond to different placement positions and angles of the cameras. In step S2 of this embodiment, a corresponding gesture detection model may be selected according to the manually inputted or automatically identified camera placement position and angle to adapt to gesture detection in the current detection environment.
Referring specifically to fig. 2, the configuration of the placement position and angle by automatic recognition specifically includes the steps of:
b1: establishing a camera detection model, and collecting or inputting a standard attitude image, wherein the camera detection model is a regression model;
b2: regression is carried out on the standard attitude image through a camera detection model, so that angles of a low head, a rotating head and a deflection head are obtained;
b3: and according to the angles of the low head, the rotary head and the offset head, reversely pushing to obtain the placement position and the angle of the camera.
In the method of the embodiment, the placing positions and angles of the cameras can be set in various ways, and because the placing positions and angles of the cameras have a great relationship with the judgment of gesture detection, different placing positions and angles correspond to different gesture detection models.
Preferably, in the present embodiment S3, the criteria for correct posture corresponding to the posture detection model may include: the distance between eyes and the table top cannot be less than 30cm, the difference of heights between two shoulders and the table top cannot be more than 2cm, the difference of heights between eyes and the table top when the eyes are in front of the table top and the table top are straight and the height when the eyes are in front of the table top, the angle of the lower head cannot be more than 45 degrees, the angle of the rotating head cannot be more than 30 degrees, the angle of the eccentric head cannot be more than 15 degrees, and when all conditions are met, the table top is in a correct posture, otherwise, the table top is in an incorrect posture. Wherein, when the eyes in front of the user are seen, the difference between the height of the eyes from the desktop and the height of the eyes in front of the user are not more than 5cm, and the standard can judge whether the user is bent at present. If the gesture detection model is adopted as a regression model, an image of the sitting body in front of the sitting body is required to be input in advance, the distance between eyes and the desktop is returned, and whether the user bends down is indirectly judged according to the current angle of the lower head and the position of the eyes from the desktop.
Preferably, when people are in different states, such as reading and writing, the requirements on the posture standard may be inconsistent, such as when writing with the right hand, people may prefer to lean to the left, where certain adjustments to the posture standard are required. If a classification model is used in A2, multiple models need to be trained according to different standards; if a regression model is used in A2, the judgment standard is only required to be modified correspondingly.
Preferably, before step S3 of this embodiment is performed, a determination as to whether gesture detection is required may be added, that is, whether there is a person in the screen and whether the person is in a suitable position, specifically, when there is no person or no person is in a suitable position in the screen, standby is performed, and otherwise step S3 is performed.
Preferably, in step S3 of this embodiment, when the posture of the user is wrong, the alarm may be given in real time, or the alarm may be given after the posture of the user is wrong for a certain time.
Example 2
Referring to fig. 3, the present application provides an adaptive posture error correction detection device based on embodiment 1, and the adaptive posture error correction detection method according to any one of the above is applied to perform posture detection, including: the device comprises a shell 3, a fixed connecting piece 1 arranged on the shell 3, and a gesture detection module, a warning module and a control module which are arranged in the shell 3;
the gesture detection module comprises a camera 10 for acquiring gesture images and a gesture judging unit for detecting the gesture images and generating regulation and control signals;
the control module is respectively connected with the gesture judging unit and the warning module in a signal way and used for controlling the warning module to warn according to the regulation and control signal, configuring configuration information of the current gesture detection state and selecting a gesture detection model of the gesture judging unit according to the configuration information.
The present embodiment will now be described in detail:
the fixing connector 1 of the present embodiment is a magnetic attraction member or a fastening member or an adhesive member or a clamping member or a locking member, supports two mounting modes of external wearing and internal mounting in other products, and can be fixed on, but not limited to, a desk, a bookshelf, a wall surface, a ground, a desk lamp, a clock and other external interfaces.
The device of the embodiment can fix the self-adaptive posture error correction detection device at any position in the environment through various fixed connecting pieces 1, and can also be combined with any object in the environment, thereby improving the self-adaptive capacity and expanding the application range.
The camera 10 of the present embodiment preferably uses a camera 10 of 100 to 300 ten thousand pixels with a view angle of 75 ° to 90 °. Preferably, the camera 10 of the present embodiment is placed at an angle perpendicular or approximately perpendicular to the horizontal plane, so as to facilitate gesture detection, further preferably, the placement position of the camera 10 uses the central axis of the human body of the user as an axis, uses the normal line of the front surface of the human body as a 0 ° reference line, the placement angle is 0 °, the left-right deviation is 5 °, the counter-clockwise rotation is 40 ° to 45 °, the height of the device from the desktop is 15cm to 35cm, and the distance from the device to the human body is 40cm to 70 cm. Similarly, the camera 10 of the present embodiment is not limited to the above configuration, and may be fixed at other placement positions and angles, and the posture detection adaptation may be performed by selecting an internal posture detection model.
Referring to fig. 3, the warning module of this embodiment includes a right-bias position warning lamp 7, an error gesture warning lamp 8, a left-bias position warning lamp 9, and a warning buzzer 4, and adopts various warning modes, such as flashing frequency of the lamp, sound of the buzzer, etc., so as to present different warning effects of different gesture errors.
The control module of the embodiment can count the maintenance time of normal posture and control the warning module to carry out tired reminding according to the maintenance time so as to prevent a user from maintaining one posture for a long time. The control module can also perform gesture judgment once every other preset time so as to reduce the frequency of gesture detection and prolong the endurance time of the device.
Referring to fig. 3, the implementation further includes a communication module 2, a charging interface 12, a data transmission port 11, and a key module 5, where the communication module 2 is electrically connected with the control module and is used to feed back the working state and the posture health report of the adaptive posture error correction detection device, the charging interface 12 is used to charge or supply power to the adaptive posture error correction detection device, the data transmission port 11 is used to perform data transmission with the outside, such as posture detection data, and the key module 5 is used to control the related operation of the module.
Specifically, the communication module 2 may communicate with an external client or device based on WIFI, bluetooth, 2G/3G/4G, etc. communication technologies, so as to upload posture related data, and preferably, the control unit may send a posture detection condition for a period of time to the mobile client via the communication module 2 to generate a posture health report for a user to refer to.
The key module 5 of the present embodiment is provided with a button 6, and the button 6 may be a physical button 6 or a virtual button 6, and specifically may perform various operations such as alarm elimination, gesture detection switch, mode selection, device reset, etc.
Preferably, the gesture determining unit is further used for a function of user identity recognition, and prompts or transmits corresponding information to the mobile client through the communication unit when new user features are recognized, so that the user is timely reminded of the identity information currently detected. The gesture determining unit may also be used for an environmental scene recognition function, collecting tool information currently used by the user through the camera 10, and the identifiable tool includes, but is not limited to, a book, a pen, a mobile phone, a tablet, etc., determining a working scene of the current user according to the identified tool information, and adjusting working parameters such as brightness, color tone, etc. of an external product through the control module on the basis of the working scene, so as to protect eyesight of the user.
Preferably, the embodiment further comprises a speaker and a microphone for voice interaction in signal connection with the control module, wherein the speaker and the microphone are also used for acoustic ranging between the device and the user to assist in adjusting the fixed position of the device. The device of this embodiment is through setting up loudspeaker and microphone, not only conveniently carries out human-computer interaction to playing the function of sound wave range finding at self-adaptation gesture error correction detection device fixed process, can assisting device's installation, when human body is too near or when too far away from the device, suggestion user adjusts device's position, so, improved self-adaptation ability, enlarged application range. Likewise, the warning module can also carry out voice warning through the loudspeaker.
Preferably, the infrared sensor is configured for the device to detect whether a person enters the effective detection range, the device detects that the person is in the effective detection range and automatically opens, and when the user leaves the effective detection range, the device automatically sleeps.
The adaptive posture error correction detection device provided by the embodiment can carry out targeted posture detection according to different crowds, prompts a user that the current posture is in an error state when detecting that the posture is wrong, stops prompting when the user returns to the correct posture, avoids the user to be in a state of being harmful to human bodies for a long time, helps the user to develop good posture habit under the premise of not limiting the actions of the user, protects the navigation for healthy driving, has a simple product structure, is easy to assemble and combine with other objects, and has great practicality on the posture detection effect.
The embodiments of the present invention have been described in detail with reference to the drawings, but the present invention is not limited to the above embodiments. Even if various changes are made to the present invention, it is within the scope of the appended claims and their equivalents to fall within the scope of the invention.
Claims (11)
1. The self-adaptive posture error correction detection method is characterized by comprising the following steps of:
s1: fixing the position of the camera and configuring configuration information of the current gesture detection state;
s2: selecting a gesture detection model according to the configuration information;
s3: the camera acquires a current gesture image and detects the gesture image through the selected gesture detection model: if the gesture is detected to be abnormal, sending out an alarm, otherwise repeating the step S3;
in the step S1, the usage environment information includes a placement position and an angle of the camera, where the placement position and the angle are configured through manual input or automatic identification;
in the step S2, the specific steps of selecting the gesture detection model according to the configuration information are as follows: selecting the gesture detection model according to the placement position and the angle, wherein the configuration information comprises user information, use environment information and a gesture image library;
the configuration of the placement position and the angle through automatic identification specifically comprises the following steps:
b1: establishing a camera detection model, and collecting or inputting a standard posture image, wherein the camera detection model is a regression model;
b2: returning the standard attitude image through the camera detection model to obtain angles of low head, turning head and offset head;
b3: and reversely pushing to obtain the placement position and angle of the camera according to the angles of the lower head, the rotating head and the eccentric head.
2. The adaptive posture error correction detection method according to claim 1, wherein the step S1 is preceded by the steps of:
a1: collecting the configuration information under different gesture detection states;
a2: and training through different configuration information to obtain a plurality of different gesture detection models.
3. The adaptive gesture correction detection method according to claim 2, wherein the gesture detection model is a classification model, and in the step A2, the gesture class is required to be labeled for the image required for training the classification model.
4. The adaptive posture error correction detection method according to claim 2, wherein the posture detection model is a regression model, and in the step A2, posture parameters need to be labeled on an image required for training the regression model.
5. The adaptive posture error correction detection method of claim 4, wherein the posture parameters include a distance of eyes from a table top, left and right shoulder heights, a low head angle, a swivel angle, a yaw angle.
6. An adaptive posture error correction detection apparatus, characterized in that it performs posture detection by applying the adaptive posture error correction detection method according to any one of claims 1 to 5, comprising: the device comprises a shell, a fixed connecting piece arranged on the shell, and a gesture detection module, a warning module and a control module which are arranged in the shell;
the gesture detection module comprises a camera for acquiring gesture images and a gesture judging unit for detecting the gesture images and generating regulation and control signals;
the control module is respectively connected with the gesture judging unit and the warning module in a signal way, and is used for controlling the warning module to warn according to the regulation and control signal, configuring configuration information of the current gesture detection state and selecting a gesture detection model of the gesture judging unit according to the configuration information.
7. The adaptive posture correction detecting device according to claim 6, wherein the fixed connection member is a magnetic attraction member or a clip member or an adhesive member or a clip member or a locking member.
8. The adaptive posture error correction detection device according to claim 6, further comprising a carrier, wherein the housing is fixed inside or outside the carrier via the fixed connection, and the carrier is a desk lamp, an audio device, a display, a water cup, a clock, a desk, or a bookshelf.
9. The adaptive type posture error correction detection device according to claim 6, further comprising a communication module electrically connected to the control module for feeding back the working state and posture health report of the adaptive type posture error correction detection device.
10. The adaptive posture error correction detection apparatus according to any one of claims 6 to 9, wherein the control module is further configured to count a maintenance time for normal posture, and control the warning module to perform tiredness warning according to the maintenance time.
11. The adaptive gesture correction detection apparatus according to any one of claims 6-9 further comprising a speaker and microphone for voice interaction in signal communication with the control module, wherein the speaker and microphone are also used for acoustic ranging between the apparatus and a user to assist in adjusting the fixed position of the apparatus.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911310507.6A CN111160165B (en) | 2019-12-18 | 2019-12-18 | Self-adaptive posture error correction detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911310507.6A CN111160165B (en) | 2019-12-18 | 2019-12-18 | Self-adaptive posture error correction detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111160165A CN111160165A (en) | 2020-05-15 |
| CN111160165B true CN111160165B (en) | 2023-12-19 |
Family
ID=70557842
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911310507.6A Active CN111160165B (en) | 2019-12-18 | 2019-12-18 | Self-adaptive posture error correction detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111160165B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113836965A (en) * | 2020-06-08 | 2021-12-24 | 北京字节跳动网络技术有限公司 | Method, device, terminal and storage medium for processing information |
| CN112998699B (en) * | 2021-04-02 | 2022-12-13 | 四川写正智能科技有限公司 | Radar sensor system for detecting user motion state and detection method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006004043A1 (en) * | 2004-07-07 | 2006-01-12 | Nec Corporation | Wide field-of-view image input method and device |
| CN103034859A (en) * | 2012-12-13 | 2013-04-10 | 华为技术有限公司 | Method and device for obtaining posture model |
| CN103955272A (en) * | 2014-04-16 | 2014-07-30 | 北京尚德智产投资管理有限公司 | Terminal equipment user posture detecting system |
| CN206674138U (en) * | 2017-04-01 | 2017-11-24 | 连云港艾加加信息科技有限公司 | Video-assisted equipment and set top box with posture error correction |
| CN109948509A (en) * | 2019-03-11 | 2019-06-28 | 成都旷视金智科技有限公司 | Obj State monitoring method, device and electronic equipment |
| CN110321786A (en) * | 2019-05-10 | 2019-10-11 | 北京邮电大学 | A kind of human body sitting posture based on deep learning monitors method and system in real time |
| CN110414419A (en) * | 2019-07-25 | 2019-11-05 | 四川长虹电器股份有限公司 | A kind of posture detecting system and method based on mobile terminal viewer |
-
2019
- 2019-12-18 CN CN201911310507.6A patent/CN111160165B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006004043A1 (en) * | 2004-07-07 | 2006-01-12 | Nec Corporation | Wide field-of-view image input method and device |
| CN103034859A (en) * | 2012-12-13 | 2013-04-10 | 华为技术有限公司 | Method and device for obtaining posture model |
| CN103955272A (en) * | 2014-04-16 | 2014-07-30 | 北京尚德智产投资管理有限公司 | Terminal equipment user posture detecting system |
| CN206674138U (en) * | 2017-04-01 | 2017-11-24 | 连云港艾加加信息科技有限公司 | Video-assisted equipment and set top box with posture error correction |
| CN109948509A (en) * | 2019-03-11 | 2019-06-28 | 成都旷视金智科技有限公司 | Obj State monitoring method, device and electronic equipment |
| CN110321786A (en) * | 2019-05-10 | 2019-10-11 | 北京邮电大学 | A kind of human body sitting posture based on deep learning monitors method and system in real time |
| CN110414419A (en) * | 2019-07-25 | 2019-11-05 | 四川长虹电器股份有限公司 | A kind of posture detecting system and method based on mobile terminal viewer |
Non-Patent Citations (1)
| Title |
|---|
| 韩晓明 ; 冉春风 ; 侯雪峰 ; 关然 ; 潘巍 ; .基于视频的学生坐姿检测与纠正系统研究.首都师范大学学报(自然科学版).2009,(S1),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111160165A (en) | 2020-05-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104239860B (en) | A kind of sitting posture detection and based reminding method and device using during intelligent terminal | |
| CN204557748U (en) | Sitting correction appliance | |
| CN105046893B (en) | A kind of sitting posture monitor and control method | |
| CN204303137U (en) | A kind of body posture monitoring terminal and system | |
| US20160026241A1 (en) | System and Method for Monitoring Habits of User of Electronic Device | |
| CN106643708A (en) | IMU-based interactive sitting posture correction device, sitting posture correction appliance and monitoring software | |
| CN111160165B (en) | Self-adaptive posture error correction detection method and device | |
| CN104484984A (en) | Adjustable detecting reminding device for human posture | |
| KR20130031120A (en) | Apparatus and method for assisting in positioning user's posture | |
| CN105788185A (en) | Method and device for monitoring sitting posture | |
| CN105411590A (en) | Human sitting posture detection and health evaluation system and method | |
| CN207281987U (en) | Learning instrument for correcting sitting posture | |
| CN109116586B (en) | Multifunctional intelligent glasses | |
| CN104461019B (en) | Bow the system and method for prompting | |
| CN105118247B (en) | A kind of spectacle-frame type Intelligent eyesight protection instrument | |
| CN105135265A (en) | Intelligent table lamp and controlling method thereof | |
| CN103908065A (en) | Intelligent desk with sitting posture correcting function and correcting method implemented by intelligent desk | |
| WO2018006839A1 (en) | Sitting posture monitoring apparatus and lighting apparatus | |
| CN110632773A (en) | Intelligent myopia prevention and control glasses | |
| CN104503537A (en) | Computer display with function of preventing myopia and lumbar vertebra and vertebral column diseases | |
| CN207946657U (en) | A kind of electronic watch based on eyesight protection system | |
| CN109255314A (en) | Information cuing method, device, intelligent glasses and storage medium | |
| CN109141346A (en) | Sitting posture corrigendum bootstrap technique, device, equipment and the storage medium of wearable device | |
| CN104867361A (en) | Intelligent terminal for interactional and situational teaching | |
| US20200046261A1 (en) | System for correcting shoulder alignment, assembly of a system and a further processing device, and a computer program product |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |