SE2051565A1 - Abnormal body posture prompt method and system - Google Patents
Abnormal body posture prompt method and systemInfo
- Publication number
- SE2051565A1 SE2051565A1 SE2051565A SE2051565A SE2051565A1 SE 2051565 A1 SE2051565 A1 SE 2051565A1 SE 2051565 A SE2051565 A SE 2051565A SE 2051565 A SE2051565 A SE 2051565A SE 2051565 A1 SE2051565 A1 SE 2051565A1
- Authority
- SE
- Sweden
- Prior art keywords
- posture
- abnormal
- prompt
- duration
- preset
- Prior art date
Links
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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Social Psychology (AREA)
- Psychiatry (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Image Analysis (AREA)
- Alarm Systems (AREA)
Abstract
The embodiments of the invention relate to an abnormal body posture prompt method and system. The method comprises: acquiring video frame data of a body posture in real time by a camera, and inputting the acquired video frame data to a preset neural network model; determining whether or not a body is in an abnormal posture by means of calculation and analysis of the preset neural network model, and recording a first duration of the body in the abnormal posture; if the first duration exceeds a first preset duration, depicting the abnormal posture of the body, carrying out an overlapping contrast between the abnormal posture and a normal posture of the body, and generating a first prompt information; and displaying the first prompt information. The abnormal body posture prompt method and system provided by the embodiments of the invention can prompt users to do physical activities properly, adjust their postures and arouse users’ awareness of the harm of abnormal postures to their bodies.
Description
ABNORIVIAL BODY POSTURE PROMPT METHOD AND SYSTEM Technical Field id="p-1"
id="p-1"
[0001] The invention relates to the technical field of artificial intelligence, in particular to an abnormal body posture prompt method and system.
Background id="p-2"
id="p-2"
[0002] In our life, many people have suffered from cervical pains or lumbarpains, one of the reasons for Which is that When our body is maintained in a fixedposture for a long time, the posture of the head and the neck Will be constant, Whichmay cause excessive motions of local parts of the cervical vertebra and the lumbarvertebra and result in injuries to these local parts, and thus, cervical pains or lumbar pains are caused. id="p-3"
id="p-3"
[0003] At present, many people Work in front of computers and have tohold themselves in one posture for a long time, and thus, most of these people havethe symptoms of cervical pains or lumbar pains. For example, IT Workers often needto Work in front of computers for hours Without a break, and consequentially, changesof their bodies, such as neck-forward, Waist sinking and spine distortion to someextent, Will occur unconsciously. Failure to adjust these changes Will aggravate thestrains of the cervical vertebra, the shoulders and the Waist, their bodies Will beirreversibly injured over time, and in server cases, headaches, dizziness and numbnessof upper limes may be caused and affect their normal life. If people having Worked inone posture for a long time can be prompted With pictures or characters to stand up todo some exercises, or people having held themselves in a sitting posture for a longtime can be guided to correct their bad sitting postures, the strains of their shouldersand Waists can be relieved to some extent. Therefore, it is necessary to solve one or more problems of the related art mentioned above. id="p-4"
id="p-4"
[0004] It should be noted that this section aims to introduce the background or context of the implementation of the invention stated in the claims, but the description in this section does not necessarily belong to the prior part.
Summa[0005] The objective of the embodiments of the invention is to provide anabnorrnal body posture prompt method and system to, at least to some extent, solve one or more problems caused by the limitations and drawbacks of the related art. id="p-6"
id="p-6"
[0006] In a first aspect, the embodiments of the invention provide an abnormal body posture prompt method, comprising: id="p-7"
id="p-7"
[0007] Acquiring video frame data of a body posture in real time by a camera, and inputting the acquired video frame data to a preset neural network model; id="p-8"
id="p-8"
[0008] Determining whether or not a body is in an abnormal posture bymeans of calculation and analysis of the preset neural network model, and recording a first duration of the body in the abnormal posture; id="p-9"
id="p-9"
[0009] Wherein the preset neural network model is used after parametersare cured therein by training multiple with positive body posture samples and negativebody posture samples, and a first preset duration of the body in the abnormal posture is set in the preset neural network model; id="p-10"
id="p-10"
[0010] If the first duration exceeds the first preset duration, depicting theabnormal posture of the body, carrying out an overlapping contrast between theabnormal posture and a normal posture of the body, and generating a first prompt information; and displaying the first prompt information; id="p-11"
id="p-11"
[0011] Wherein the first prompt information includes overlapping contrastimage information of the abnormal posture and the normal posture and/or trainingaction information, and the training action information is generated by aiming at asingle abnormal body posture and/or a combination of multiple abnormal body postures. id="p-12"
id="p-12"
[0012] In one embodiment of the inVention, the method further comprises: id="p-13"
id="p-13"
[0013] If the body is in normal posture, recording a second duration of the body in the norrnal posture; and id="p-14"
id="p-14"
[0014] If the second duration exceeds a second preset duration, generating asecond prompt inforrnation, and displaying the second prompt inforrnation on a terrninal display interface. id="p-15"
id="p-15"
[0015] Wherein the second preset duration is a duration of the body in thenorrnal posture set in the preset neural network model, and the second prompt inforrnation includes rest prompt inforrnation and/or basic training action inforrnation. id="p-16"
id="p-16"
[0016] In one embodiment of the invention, the body posture includes a neck posture, a shoulder posture and/or a waist posture. id="p-17"
id="p-17"
[0017] In one embodiment of the inVention, depicting the abnormal postureof the body includes depicting contour lines of the body to generate a body contour drawing. id="p-18"
id="p-18"
[0018] In one embodiment of the inVention, the first preset duration is 20 minutes; and/or, the second preset duration is 40 minutes. id="p-19"
id="p-19"
[0019] In a second aspect, the embodiments of the invention provide an abnormal body posture prompt system, comprising: id="p-20"
id="p-20"
[0020] A camera unit used for acquiring video frame data of a body posturein real time by a camera and inputting the acquired Video frame data to a preset neural network model; id="p-21"
id="p-21"
[0021] An analysis unit used for calculation and analysis of the preset neural network model; id="p-22"
id="p-22"
[0022] A deterrnining unit used for deterrnining whether or not a body is in an abnormal posture; id="p-23"
id="p-23"
[0023] A recording unit used for recording a first duration of the body in the abnorrnal posture; id="p-24"
id="p-24"
[0024] Wherein the preset neural network model is used after parametersare cured therein by training multiple with positive body posture samples and negativebody posture samples, and a first preset duration of the body in the abnorrnal posture is set in the preset neural network model; and id="p-25"
id="p-25"
[0025] The deterrnining unit is used for deterrnining whether or not the first duration exceeds the first preset duration; id="p-26"
id="p-26"
[0026] A depicting unit used for depicting the abnorrnal posture of the bodyand carrying out an oVerlapping contrast between the abnorrnal posture and a normal posture of the body; id="p-27"
id="p-27"
[0027] A prompt unit used for generating a first prompt information; and id="p-28"
id="p-28"
[0028] A display unit used for displaying the first prompt information; id="p-29"
id="p-29"
[0029] Wherein the first prompt information includes oVerlapping contrastimage information of the abnorrnal posture and the normal posture and/or trainingaction information; the training action information is generated by aiming at a single abnorrnal body posture and/or a combination of multiple abnorrnal body postures. id="p-30"
id="p-30"
[0030] In one embodiment of the invention, when the body is in the normalposture, the recording unit is used for recording a second duration of the body in the normal posture; id="p-31"
id="p-31"
[0031] The prompt unit is used for generating a second prompt information when the second duration exceeds a second preset duration; id="p-32"
id="p-32"
[0032] The display unit is used for displaying the second prompt information; id="p-33"
id="p-33"
[0033] Wherein, the second preset duration is a duration of the body in thenorrnal posture set through the preset neural network model, and the second prompt inforrnation includes rest prompt inforrnation and/or basic training action inforrnation. id="p-34"
id="p-34"
[0034] In one embodiment of the invention, the body posture includes a neck posture, a shoulder posture and/or a waist posture. id="p-35"
id="p-35"
[0035] In one embodiment of the invention, depicting the abnorrnal postureof the body includes depicting contour lines of the body to generate a body contour drawing. id="p-36"
id="p-36"
[0036] In one embodiment of the invention, the first preset duration is 20 minutes; and/or, the second preset duration is 40 minutes. id="p-37"
id="p-37"
[0037] The technical solution provided by the embodiments of the invention has the following benef1cial effects: id="p-38"
id="p-38"
[0038] According to the abnorrnal body posture prompt method and systemprovided by the embodiments of the invention, an abnorrnal posture of the body iscalculated and analyzed using a preset neural network model; when the duration ofthe body in the abnorrnal posture exceeds a preset duration, the abnorrnal posture ofthe body is depicted to generate a contour drawing and is subjected to an overlappingcontrast with a normal posture of the body to generate a contrast image, which is thensent to a terminal together with training action inforrnation to prompt users to dophysical activities properly, adjust their postures and arouse users” awareness of the harrn of abnorrnal postures to their bodies.
Brief Description of the Drawings id="p-39"
id="p-39"
[0039] The drawings, incorporated into the specification and constituting one part of the specif1cation, illustrate feasible embodiments of the disclosure and areused to explain the principle of the disclosure together with the specif1cation.Obviously, the drawings in the following description merely illustrate someembodiments of the disclosure, and those ordinarily skilled in the art can obtain otherdrawings according to the following ones without creative labor. id="p-40"
id="p-40"
[0040] FIG. l illustrates a flow diagram of an abnorrnal body postureprompt method in an illustrative embodiment of the invention; id="p-41"
id="p-41"
[0041] FIG. 2 illustrates a frame diagram of an abnorrnal body postureprompt system in the illustrative embodiment of the invention; id="p-42"
id="p-42"
[0042] FIG. 3 illustrates a schematic diagram of abnorrnal body postures inthe illustrative embodiment of the invention; id="p-43"
id="p-43"
[0043] FIG. 4 illustrates an overlapping contrast diagram of an abnorrnalbody posture and a normal body posture in the illustrative embodiment of theinvention; id="p-44"
id="p-44"
[0044] FIG. 5 illustrates a schematic diagram of training actions in the illustrative embodiment of the invention.
Detailed Description of Embodiments id="p-45"
id="p-45"
[0045] Illustrative embodiments will be more comprehensively describedbelow with reference to the accompanying drawings. Clearly, the illustrativeembodiments may be implemented in different forms, and should not be limited to theforms expounded herein. These illustrative embodiments are provided to make theinvention more comprehensive and completed and to convey the conception of theillustrative embodiments to those skilled in the art comprehensively. The features,structures or properties described below can be combined in one or moreembodiments in any suitable manners. id="p-46"
id="p-46"
[0046] In addition, the accompanying drawings are merely illustrativedrawings of the embodiments of the invention, and are not necessarily drawn to scale.
Identical reference signs in the drawings represent identical or similar parts, so repeated descriptions of these identical reference signs are omitted. Some blockdiagrams in the accompanying drawings illustrate functional entities and do notnecessarily correspond to physically or logically independent entities. id="p-47"
id="p-47"
[0047] This illustrative embodiment first provides an abnorrnal bodyposture prompt method. Referring to FIG. 1, the method may comprise: id="p-48"
id="p-48"
[0048] S101: video frame data of a body posture are acquired in real timeby a camera, and the acquired video frame data is input to a preset neural networkmodel; id="p-49"
id="p-49"
[0049] S102: whether or not a body is in an abnorrnal posture is deterrninedby means of calculation and analysis of the preset neural network model, and a firstduration of the body in the abnorrnal posture is recorded, wherein the preset neuralnetwork model is used after parameters are cured therein by training multiple withpositive body posture samples and negative body posture samples, and a first presetduration of the body in the abnorrnal posture is set in the preset neural network model; id="p-50"
id="p-50"
[0050] S103: if the first duration exceeds the first preset duration, theabnorrnal posture of the body is depicted and is subjected to an overlapping contrastwith a normal posture of the body, and a first prompt information is generated,wherein the first prompt information includes overlapping contrast image informationof the abnorrnal posture and the normal posture and/or training action information,and the training action information is generated by aiming at a single abnorrnal bodyposture and/or a combination of multiple abnorrnal body postures. id="p-51"
id="p-51"
[0051] S104: the first prompt information is displayed. id="p-52"
id="p-52"
[0052] According to the abnorrnal body posture prompt method describedabove, an abnorrnal posture of the body is calculated and analyzed using a presetneural network model; when the duration of the body in the abnorrnal posture exceedsa preset duration, the abnorrnal posture of the body is depicted to generate a contourdrawing and is subj ected to an overlapping contrast with a normal posture of the bodyto generate a contrast image, which is then sent to a terminal together with trainingaction information to prompt users to do physical activities properly, adjust their postures and arouse users” awareness of the harrn of abnorrnal postures to their bodies. id="p-53"
id="p-53"
[0053] Below, the steps of the abnormal body posture prompt method inthis illustrative embodiment will be explained in further detail with reference to FIG.1 to FIG. 5. id="p-54"
id="p-54"
[0054] S101: video frame data of a body posture is acquired in real time bya camera, and the acquired video frame data is input to a preset neural network model. id="p-55"
id="p-55"
[0055] Illustratively, considering that people often work, study or useelectronic products in abnormal postures such as a head-down posture, a neck-forwardposture and a waist sinking posture, and may hold themselves in the abnormalpostures for a long time, this embodiment provides an abnormal body posture promptmethod to prompt people to adjust their posture in time to avoid injuries to theirbodies caused by long-terrn exposure to these abnormal postures. According to theabnormal body posture prompt method, video frame data of a body posture isacquired in real time by a camera, and a neural network model is preset, wherein theneural network is a complicated network system formed by a great deal of simpleprocessing units (referred to as nerve cells) that are extensively connected, reflectsmany essential features of human brains, and is an extremely complicated nonlineardynamic learning system. The neural network has the capacities of mass parallel anddistributed storage and processing, self-organization, self-adaption and self-learning.An acquisition unit in the camera inputs the video frame data acquired by the camerato the preset neural network model. The neural network may be, but is not limited to,a BP neural network that can learn and store a large quantity of input-output modemapping relations without revealing a mathematical equation for describing thesemapping relations in advance. Specific details can be understood with reference to theprior art, and will not be given anymore here. id="p-56"
id="p-56"
[0056] S102: whether or not a body is in an abnormal posture is deterrninedby means of calculation and analysis of the preset neural network model, and a firstduration of the body in the abnormal posture is recorded, wherein the preset neuralnetwork model is used after parameters are cured therein by training multiple with positive body posture samples and negative body posture samples, and a first preset duration of the body in the abnormal posture is set in the preset neural network model. id="p-57"
id="p-57"
[0057] Illustratively, the preset neural network model is used afterparameters are cured therein by training multiple with positive body posture samplesand negative body posture samples, wherein the positive samples are samplescorresponding to correct categories to be classified, and in this embodiment, thepositive samples correspond to the body in video frames and may specificallycorrespond to the shoulders and waist of users; the negative samples may correspondto other objects except the body, such as desks, chairs, and computers. After theparameters are cured in the neural network model and the video frame data of thebody posture is input to the neural network model in real time, the neural networkmodel will output a posture status and record the durations of different abnormalpostures. For example, the camera will acquire the video frame data of the bodyposture in real time; if a user is in a head-down posture, data of the head-downposture will be calculated and analyzed according to the video frame data input to theneural network model to determine that the user is in a head-down status at thismoment, the abnormal posture is output, and a first duration of the user in thehead-down posture is recorded. In one example, the body posture includes, but is notlimited to, a neck posture and/or a shoulder posture and/or a waist posture. The bodyposture may also be a leg posture to recognize the posture of users who are used tocrossing their legs and to give a prompt to the users. id="p-58"
id="p-58"
[0058] S103: if the first duration exceeds the first preset duration, theabnormal posture of the body is depicted and is subjected to an overlapping contrastwith a normal posture of the body, and a first prompt information is generated,wherein the first prompt information includes overlapping contrast image informationof the abnormal posture and the normal posture and/or training action information,and the training action information is generated by aiming at a single abnormal bodyposture and/or the combination of multiple abnormal body postures. id="p-59"
id="p-59"
[0059] Illustratively, the neural network model can transmit an outputabnormal posture signal to a recording module, which in tum records the duration of the abnormal posture; when the duration exceeds a preset duration, the neural network model transmits Video frames, namely an image, of the abnormal posture of the bodyto a depicting module, then the depicting module depicts contour lines of the body inthe abnormal posture to generate a contour drawing and carries out an oVerlappingcontrast between the contour drawing and a drawing of the body in a normal posture,and then first prompt information is generated and is sent to a terminal module to givea prompt to the user that the body is in the abnormal posture at this moment. Forexample, the neural network model deterrnines a head-forward posture of the body as an abnormal posture, and the output duration of the abnormal posture, namely the duration of the head-forward posture of the body, is recorded by the recording module.
In one example, the first preset duration is, but not limited to, 20 minutes and can beset as the case may be. When the duration of the abnormal posture exceeds the firstpreset duration, namely 20 minutes, the depicting module will depict a contourdrawing of the body in the head-forward posture at this moment according to Videoframes of the abnormal posture. In one example, depicting the abnormal posture ofthe body includes depicting contour lines of the body to generate a body contourdrawing. Body image data can be extracted according to the Video frame data of theabnormal posture of the body, the abnormal posture is depicted according to theimage data to generate the contour drawing of the body, and an oVerlapping contrastis carried out between the contour drawing of the body in the abnormal posture and adrawing of the body in the normal posture to display the degree of forward tilting ofthe head of the body, so that the user can obtain an intuitiVe sense and can adjust theposture to some extent. After the oVerlapping contrast between the drawings iscompleted, the neural network model can generate a piece of prompt informationincluding an oVerlapping contrast image of the drawings, information about the harrncaused by long-terrn exposure to the abnormal posture and information about trainingactions aiming at the abnormal posture, and the prompt information is sent to theterminal module through a communication module and is displayed by the terminalmodule.[0060] S104: the first prompt information is displayed. id="p-61"
id="p-61"
[0061] Specifically, the first prompt information can be displayed on a terminal display interface of a terminal, such as one comer of a computer, to inforrnthe user of the part, in the abnorrnal posture, of the body and the harrn of the abnorrnalposture, and 2-3 sets of simple training actions can be displayed to help the user carryout training to relieVe injuries of the abnormal posture to the body. The training actioninformation may include training actions generated by aiming at a single abnormalposture or the combination of multiple abnormal postures. For example, if the body isonly exposed to a head-forward posture, the training action information merely aimsat the head; if the body is only exposed to a waist sinking or distortion posture, thetraining action information merely aims at the waist; if the body is exposed toabnormal postures of the head, the shoulders and the waist, the training informationaims at the head, the shoulders and the waist. id="p-62"
id="p-62"
[0062] In one embodiment, the method further comprises 81031: if thebody is in the normal posture, a second duration of the body in the normal posture isrecorded; 81032: if the second duration exceeds a second preset duration, a secondprompt information is generated and is displayed on the terminal display interface,wherein the second preset duration is a duration of the body in the normal posture setin the preset neural network model, and the second prompt information includes restprompt information and/or basic training action information. id="p-63"
id="p-63"
[0063] Illustratively, when the body posture output by the neural networkmodel is a normal posture, the output duration of the normal posture is recorded bythe recording module; when the duration exceeds a preset duration, promptinformation will be generated and sent to the terminal module. Illustratively, thesecond preset duration is 40 minutes. When the body is exposed to the normal postureoVer 40 minutes, the neural network model will send the rest prompt information andthe basic training action information to a mobile phone or a computer to prompt usersthat they should drink water or do a set of basic actions to relax their bodies. id="p-64"
id="p-64"
[0064] This illustrative embodiment further provides an abnormal bodyposture prompt system. Referring to FIG. 2, the system may comprise: a camera unit,an analysis unit, a deterrnining unit, a recording unit, a depicting unit, a prompt unit and a display unit. id="p-65"
id="p-65"
[0065] The camera unit is used for acquiring video frame data of a bodyposture in real time by a camera and inputting the acquired video frame data to apreset neural network model; id="p-66"
id="p-66"
[0066] The analysis unit is used for calculation and analysis of the presetneural network model; id="p-67"
id="p-67"
[0067] The deterrnining unit is used for deterrnining whether or not a bodyis in an abnormal posture; id="p-68"
id="p-68"
[0068] The recording unit is used for recording a first duration of the bodyin the abnormal posture; id="p-69"
id="p-69"
[0069] Wherein, the preset neural network model is used after parametersare cured therein by training multiple with positive body posture samples and negativebody posture samples, and a first preset duration of the body is in the abnormalposture is set in the preset neural network model; id="p-70"
id="p-70"
[0070] The deterrnining unit is used for deterrnining whether or not the firstduration exceeds the first preset duration; id="p-71"
id="p-71"
[0071] The depicting unit is used for depicting the abnormal posture of thebody and carrying out an overlapping contrast between the abnormal posture and anormal posture of the body; id="p-72"
id="p-72"
[0072] The prompt unit is used for generating a first prompt information; id="p-73"
id="p-73"
[0073] The display unit is used for displaying the first prompt information; id="p-74"
id="p-74"
[0074] Wherein, the first prompt information includes overlapping contrastimage information of the abnormal posture and the normal posture and/or trainingaction information, and the training action information is generated by aiming at asingle abnormal body posture and/or the combination of multiple abnormal bodypostures. id="p-75"
id="p-75"
[0075] The specific implementation of the system can be understood withreference to the above embodiment, and will not be detailed anymore here. id="p-76"
id="p-76"
[0076] In one example, when the body is in the normal posture, therecording unit is used for recording a second duration of the body in the normal posture; id="p-77"
id="p-77"
[0077] The prompt unit is used for generating a second prompt informationwhen the second duration exceeds a second preset duration; id="p-78"
id="p-78"
[0078] The display unit is used for displaying the second promptinforrnation; id="p-79"
id="p-79"
[0079] Wherein, the second preset duration is a duration of the body in thenorrnal posture set through the preset neural network model, and the second promptinforrnation includes rest prompt inforrnation and/or basic training action inforrnation. id="p-80"
id="p-80"
[0080] In one example, the body posture includes a neck posture and/or ashoulder posture and/or a waist posture. id="p-81"
id="p-81"
[0081] In one example, depicting the abnormal body posture includesdepicting contour lines of the body to generate a body contour drawing. id="p-82"
id="p-82"
[0082] In one example, the first preset duration is 20 minutes; and/or, thesecond preset duration is 40 minutes. id="p-83"
id="p-83"
[0083] According to the abnormal body posture prompt system describedabove, an abnormal posture of the body is calculated and analyzed using a presetneural network model; when the duration of the body in the abnormal posture exceedsa preset duration, the abnormal posture of the body is depicted to generate a contourdrawing and is subj ected to an overlapping contrast with a normal posture of the bodyto generate a contrast image, which is then sent to a terminal together with trainingaction inforrnation to prompt users to do physical activities properly, adjust theirpostures and arouse users” awareness of the harrn of abnormal postures to theirbodies. id="p-84"
id="p-84"
[0084] It should be noted that the terms such as central, lengthwise, crosswise, length, width, thickness , upper, lower, front, back, left, right, Vertical, horizontal, top, bottom, inner , outer , clockwise and anticlockwise in the above description are used to indicate directional or positionalrelations on the basis of the drawings merely for the purpose of facilitating andsimplifying the description of the embodiments of the invention, do not indicate or imply that devices or elements referred to must be in a specific direction or must be configured or operated in a specific direction, and thus should not be construed as limitations of the embodiments of the invention. id="p-85"
id="p-85"
[0085] In addition, the terms first and second are merely for thepurpose of description, should not be construed as indications or implications ofrelative importance or implicit indications of the number of technical features referredto. Thus, in case where a feature defined by first or second, it may explicitly orimplicitly indicate that one or more said features are included. In the description ofthe embodiments of the invention, ““multiple” refers to two or more, unless otherwisespecifically defined. id="p-86"
id="p-86"
[0086] In the embodiments of the invention, unless otherwise expresslystated or defined, the terms such as install, link, connect and fix should bebroadly understood, which for example, may refer to fixed connection, detachableconnection or integral connection, or mechanical connection or electrical connection,or direct connection or indirect connection Via an interrnediate, or intemalcommunication of two elements or interaction of two elements. Those ordinarilyskilled in the art can appreciate the specific meaning of these terms in the invention asthe case may be. id="p-87"
id="p-87"
[0087] In the embodiments of the invention, unless otherwise expresslystated or defined, the expression that a first feature is located above or below asecond feature may include the case where the first feature directly makes contactwith the second feature and the case where the first feature makes contact with thesecond feature through another feature rather than directly making contact with thesecond feature. In addition, the expression that a first feature is located “over” or“above” a second feature or located on an “upper side” of the second feature meansthat the first feature is located over or above the second feature or means that the firstfeature is horizontally higher than the second feature. The expression that a firstfeature is located “under” or “below” a second feature or located on a “lower side” ofa second feature means that the first feature is located under or below the secondfeature or means that the first feature is horizontally lower than the second feature. id="p-88"
id="p-88"
[0088] In the specification, the description of the reference term one embodiment, some embodiments, example, specific example or some examples is intended to point out that the specific features, structures, materials ofCharacteristics incorporated in said embodiment or example are included in at leastone embodiment or example of the inVention. In this specification, the illustrativedescription of this term does not necessarily refer to one embodiment or example. Inaddition, the specific features, structures, materials or characteristics referred to maybe incorporated in one or more embodiments or examples in any suitable manners.Moreover, those skilled in the art can integrate and combine different embodiments orexamples described in this specification. id="p-89"
id="p-89"
[0089] By reading the specification and implementing the inVention, thoseskilled in the art can easily come up With other embodiments of the inVention. Theapplication is intended to include any transforrnations, usage, or adaptive Variations ofthe inVention, Which follow the basic principle of the inVention and include commonknowledge or technical means, not disclosed by the invention, of the prior art. Thespecification and embodiments are merely for an illustrative purpose, and the essential scope and spirit of the invention should be defined by the appended claims.
Claims (10)
1. An abnormal body posture prompt method, comprising: acquiring Video frame data of a body posture in real time by a camera, and inputtingthe acquired Video frame data to a preset neural network model; deterrnining whether or not a body is in an abnormal posture by means of calculationand analysis of the preset neural network model, and recording a first duration of the body inthe abnormal posture, wherein the preset neural network model is used after parameters arecured therein by training with multiple positive body posture samples and negative bodyposture samples, and a first preset duration of the body in the abnormal posture is set in thepreset neural network model; if the first duration exceeds the first preset duration, depicting the abnormal postureof the body, carrying out an oVerlapping contrast between the abnormal posture and a normalposture of the body, and generating a first prompt information; and displaying the first prompt information, wherein the first prompt informationincludes oVerlapping contrast image information of the abnormal posture and the normalposture and/or training action information, and the training action information is generated byaiming at a single abnormal body posture and/or a combination of multiple abnormal body postures.
2. The abnormal body posture prompt method according to claim l, furthercomprising: if the body is in normal posture, recording a second duration of the body in thenormal posture; and if the second duration exceeds a second preset duration, generating a second promptinformation, and displaying the second prompt information on a terminal display interface; wherein the second preset duration is a duration of the body in the normal posture setin the preset neural network model, and the second prompt information includes rest prompt information and/or basic training action information.
3. The abnormal body posture prompt method according to claim 2, wherein the body posture includes a neck posture, a shoulder posture and/or a waist posture.
4. The abnormal body posture prompt method according to claim 3, whereindepicting the abnorrnal posture of the body includes depicting contour lines of the body to generate a body contour drawing.
5. The abnorrnal body posture prompt method according to claim 4, wherein the first preset duration is 20 minutes; and/or the second preset duration is 40 minutes.
6. An abnorrnal body posture prompt system, comprising: a camera unit used for acquiring Video frame data of a body posture in real time by acamera and inputting the acquired Video frame data to a preset neural network model; an analysis unit used for calculation and analysis with the preset neural networkmodel; a deterrnining unit used for deterrnining whether or not a body is in an abnorrnalposture; a recording unit used for recording a first duration of the body in the abnorrnalposture, wherein the preset neural network model is used after parameters are cured therein bytraining with multiple positive body posture samples and negative body posture samples, afirst preset duration of the body in the abnorrnal posture is set in the preset neural networkmodel, and the deterrnining unit is used for deterrnining whether or not the first durationexceeds the first preset duration; a depicting unit used for depicting the abnorrnal posture of the body and carrying outan oVerlapping contrast between the abnorrnal posture and a normal posture of the body; a prompt unit used for generating a first prompt information; and a display unit used for displaying the first prompt information; wherein the first prompt information includes oVerlapping contrast imageinformation of the abnorrnal posture and the normal posture and/or training action information, and the training action information is generated by aiming at a single abnorrnal body posture and/or a combination of multiple abnormal body postures.
7. The abnormal body posture prompt system according to claim 6, Wherein When thebody is in the normal posture, the recording unit is used for recording a second duration of thebody in the normal posture; the prompt unit is used for generating a second prompt information When the secondduration exceeds a second preset duration; the display unit is used for displaying the second prompt information; Wherein the second preset duration is a duration of the body in the normal posture setin the preset neural network model, and the second prompt information includes rest prompt information and/or basic training action information.
8. The abnormal body posture prompt system according to claim 7, Wherein the body posture includes a neck posture, a shoulder posture and/or a Waist posture.
9. The abnormal body posture prompt system according to claim 8, Whereindepicting the abnormal posture of the body includes depicting contour lines of the body to generate a body contour draWing.
10. The abnormal body posture prompt system according to claim 9, Wherein the first preset duration is 20 minutes; and/or the second preset duration is 40 minutes.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010696314.5A CN111860311A (en) | 2020-07-20 | 2020-07-20 | Method and system for prompting abnormal posture of human body |
| PCT/CN2020/105200 WO2021047315A2 (en) | 2020-07-20 | 2020-07-28 | Method and system for notification of abnormal posture of human body |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| SE2051565A1 true SE2051565A1 (en) | 2021-03-18 |
Family
ID=73001934
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| SE2051565A SE2051565A1 (en) | 2020-07-20 | 2020-07-28 | Abnormal body posture prompt method and system |
Country Status (5)
| Country | Link |
|---|---|
| CN (1) | CN111860311A (en) |
| AU (1) | AU2020104278A4 (en) |
| SE (1) | SE2051565A1 (en) |
| WO (1) | WO2021047315A2 (en) |
| ZA (1) | ZA202007887B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113989856A (en) * | 2021-12-13 | 2022-01-28 | 周清 | Mode identification integrated service system based on heterogeneous software interface |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112613440A (en) * | 2020-12-29 | 2021-04-06 | 北京市商汤科技开发有限公司 | Attitude detection method and apparatus, electronic device and storage medium |
| CN114601478B (en) * | 2022-05-11 | 2022-09-02 | 西南交通大学 | Method, device and equipment for improving alertness of driver and readable storage medium |
| CN116580424A (en) * | 2023-05-05 | 2023-08-11 | 深圳市领天智杰科技有限公司 | Myopia prevention method and device based on neural network |
| CN116912596B (en) * | 2023-08-04 | 2024-03-22 | 无锡学院 | Multi-source data normalization processing and fusion method and system |
| CN117523936B (en) * | 2023-11-07 | 2024-06-18 | 中国人民解放军中部战区总医院 | Interactive wounded rescue skill training method and system based on evaluation feedback |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150375083A1 (en) * | 2014-06-05 | 2015-12-31 | Zih Corp. | Method, Apparatus, And Computer Program Product For Enhancement Of Event Visualizations Based On Location Data |
| CN106055460A (en) * | 2016-05-26 | 2016-10-26 | 广东欧珀移动通信有限公司 | Anti-addiction prompt method, and device of mobile terminal and mobile terminal |
| TWI669681B (en) * | 2017-11-30 | 2019-08-21 | 財團法人資訊工業策進會 | Electronic calculatiing apparatus, system, and method for providing body posture health information |
| CN108154104B (en) * | 2017-12-21 | 2021-10-15 | 北京工业大学 | Human body posture estimation method based on depth image super-pixel combined features |
| CN108256433B (en) * | 2017-12-22 | 2020-12-25 | 银河水滴科技（北京）有限公司 | Motion attitude assessment method and system |
| CN112169297A (en) * | 2018-03-05 | 2021-01-05 | 蚌埠珠领智能科技有限公司 | Working method of body movement comprehensive training device |
| CN109919034A (en) * | 2019-01-31 | 2019-06-21 | 厦门大学 | A kind of identification of limb action with correct auxiliary training system and method |
| 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 |
| CN111091046A (en) * | 2019-10-28 | 2020-05-01 | 北京灵鹦科技有限公司 | User bad sitting posture correction system based on machine vision |
| CN111104905B (en) * | 2019-12-19 | 2024-02-02 | 北京奇艺世纪科技有限公司 | Sitting posture adjusting method and device, electronic equipment and storage medium |
-
2020
- 2020-07-20 CN CN202010696314.5A patent/CN111860311A/en active Pending
- 2020-07-28 SE SE2051565A patent/SE2051565A1/en not_active Application Discontinuation
- 2020-07-28 WO PCT/CN2020/105200 patent/WO2021047315A2/en active Application Filing
- 2020-12-17 ZA ZA2020/07887A patent/ZA202007887B/en unknown
- 2020-12-23 AU AU2020104278A patent/AU2020104278A4/en active Active
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113989856A (en) * | 2021-12-13 | 2022-01-28 | 周清 | Mode identification integrated service system based on heterogeneous software interface |
| CN113989856B (en) * | 2021-12-13 | 2024-01-05 | 周清 | Pattern recognition integrated service system based on heterogeneous software interface |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021047315A3 (en) | 2021-06-17 |
| CN111860311A (en) | 2020-10-30 |
| AU2020104278A4 (en) | 2021-04-08 |
| ZA202007887B (en) | 2021-09-29 |
| WO2021047315A2 (en) | 2021-03-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| SE2051565A1 (en) | Abnormal body posture prompt method and system | |
| Fernandez et al. | Live psychotherapy by video versus in‐person: A meta‐analysis of efficacy and its relationship to types and targets of treatment | |
| Bindemann et al. | Who can recognize unfamiliar faces? Individual differences and observer consistency in person identification. | |
| SE2051569A1 (en) | Intelligent training aiding method and system for instructional cars | |
| IL297445A (en) | Mixed reality spatial audio | |
| US20150193651A1 (en) | System and method for validating test takers | |
| IL273338A (en) | Methods, systems, and media for detecting spoofing in mobile authentication | |
| Fitzgerald et al. | Comparing the effectiveness of virtual reality and video modelling as an intervention strategy for individuals with Autism Spectrum Disorder: Brief report | |
| CN105654803A (en) | Head-mounted online examination machine | |
| CN111796676A (en) | AI (Artificial intelligence) interactive auxiliary learning system and learning method | |
| Mao et al. | Binocular imbalance in amblyopia depends on spatial frequency in binocular combination | |
| Plazas et al. | Formation of new stimulus equivalence classes by exclusion | |
| Ohlsson et al. | Screening for amblyopia and strabismus with the Lang II stereo card | |
| Damewood et al. | Ultrasound simulation utilization among point of care ultrasound users: Results of a survey | |
| Joseph et al. | Proportion of refractive error and its associated factors among high school students in South India | |
| Khalil et al. | Does assistive technology help children having disabilities in Middle East and North Africa (MENA) region: a literature review | |
| Gribbins et al. | An exploration of instructors' perceptions about online proctoring and its value in ensuring academic integrity | |
| Frenzel et al. | Using student produced videos to increase knowledge of self-care topics and nonprescription medications | |
| Chee et al. | Assessing the use of a smartphone app to teach eye screening to opticians | |
| Tomlin et al. | Efficacy of a deficit specific auditory training program for remediation of temporal patterning deficits | |
| Ichikawa et al. | Two‐to three‐month‐old infants prefer moving face patterns to moving top‐heavy patterns | |
| SE544734C2 (en) | Image processing device, thermal image generation system, program, and recording medium | |
| Barnes et al. | The Friendly Schools initiative: Evidence-based bullying prevention in Australian schools | |
| IL305735A (en) | Inference device | |
| Mustonen et al. | Upper nasal hemifield location and nonspatial auditory tones accelerate visual detection during dichoptic viewing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| NAV | Patent application has lapsed |