Movatterモバイル変換


[0]ホーム

URL:


CN107050774B - A kind of body-building movement error correction system and method based on movement acquisition - Google Patents

A kind of body-building movement error correction system and method based on movement acquisition
Download PDF

Info

Publication number
CN107050774B
CN107050774BCN201710346230.7ACN201710346230ACN107050774BCN 107050774 BCN107050774 BCN 107050774BCN 201710346230 ACN201710346230 ACN 201710346230ACN 107050774 BCN107050774 BCN 107050774B
Authority
CN
China
Prior art keywords
movement
building
key point
builder
dimensional
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.)
Expired - Fee Related
Application number
CN201710346230.7A
Other languages
Chinese (zh)
Other versions
CN107050774A (en
Inventor
张海朝
龚璞
苏凡云
王卯卯
袁悦栋
纪璇
钟力
汤子尧
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Dianji University
Original Assignee
Shanghai Dianji University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai Dianji UniversityfiledCriticalShanghai Dianji University
Priority to CN201710346230.7ApriorityCriticalpatent/CN107050774B/en
Publication of CN107050774ApublicationCriticalpatent/CN107050774A/en
Application grantedgrantedCritical
Publication of CN107050774BpublicationCriticalpatent/CN107050774B/en
Expired - Fee Relatedlegal-statusCriticalCurrent
Anticipated expirationlegal-statusCritical

Links

Classifications

Landscapes

Abstract

Translated fromChinese

本发明提供了一种基于动作采集的健身动作纠错系统及方法,包括如下步骤:在显示器上播放标准人体三维骨架模型的健身动作;采集健身者在不同视角的健身动作的图像;将拍摄到的健身者的健身图像转为数字信号后进行处理得出健身者各关键点的三维坐标;根据健身者各关键点的三维坐标建立健身者的人体三维骨架模型;将建立的人体三维骨架模型的健身动作与标准的人体三维骨架模型的健身动作进行比对,以判定健身者的动作与标准健身动作是否在误差范围内:若健身者的局部动作超过误差范围提醒用户予以矫正。本发明实现了健身动作的教程及指导错误的健身动作,可以在健身时迅速的判定出健身者的错误动作并进行语音警示,从而规范健身者的健身动作。

The present invention provides a fitness action error correction system and method based on action collection, comprising the following steps: playing fitness actions of a standard three-dimensional skeleton model of a human body on a display; The fitness image of the fitness person is converted into a digital signal and processed to obtain the three-dimensional coordinates of each key point of the fitness person; according to the three-dimensional coordinates of each key point of the fitness person, the body 3D skeleton model of the fitness person is established; The fitness movements are compared with the fitness movements of the standard three-dimensional skeleton model of the human body to determine whether the exerciser's movements are within the error range of the standard fitness movements: if the exerciser's local movements exceed the error range, the user is reminded to correct them. The invention realizes the training of fitness actions and guides wrong fitness actions, and can quickly determine the wrong actions of the fitness person and give a voice warning when exercising, so as to standardize the fitness action of the fitness person.

Description

A kind of body-building movement error correction system and method based on movement acquisition
Technical field
The present invention relates to one kind to acquire more people based on CCD (Charge-coupled Device, charge coupled cell) movementThe applicable body-building of group acts error correction system, and in particular to acts error correction system to a kind of body-building based on movement acquisition, appliesHuman action acquisition and analytical technology, digital-to-analogue conversion technology, human body three-dimensional skeleton modeling technique etc., mainly with CCD camera fromHuman body different direction carries out movement acquisition, utilizes DSP (Digital Signal Processing, Digital Signal Processing, abbreviationDSP) processor carries out the motion images information processing technology and acts the error correction system analyzed to body-building.
Background technique
Body-building equipment mainly includes single function training aids and multifunctional trainer in the market at present, but these equipment only haveOperation instructions are labeled with application method and step in the side of equipment, if but unprofessional during body-buildingFitness's guidance, body builder carry out body-building just can not know whether the movement of oneself is quasi- according to the movement marked on equipmentReally;And present body-building equipment is designed primarily directed to all non-physical disabilities, but the disabled also has the need of body-building in lifeIt asks, so the present exercise guide system designed for physical disabilities is very few.
With the development of the society, the consciousness of national body-building gradually increases, people increasingly pay attention to the raising of physical fitness, butBe resulted in since the expense of the gymnasiums such as personal coach is out of the ordinary many people body-building movement it is nonstandard, make that body builder's is strongBody is not up to expected effect.
Body-building equipment mainly includes single function training aids and multifunctional trainer in the market at present, but these equipment only haveOperation instructions are labeled with application method and step in the side of equipment, if but unprofessional during body-buildingFitness's guidance, body builder carry out body-building just can not know whether the movement of oneself is quasi- according to the movement marked on equipmentReally.
It only proposes to show out the standard operation trained on a display screen in current intelligent body-building system scheme, can not markThe malfunction for remembering and showing body builder, such as the patent of invention of Publication No. CN101791466A, the intelligence with coach functionBody-building system is the movement of body builder to be acquired based on the sensor on fitness equipment, but require on each fitness equipment moreA sensor, and the price of professional sensor is costly, so that body-building increased costs, and body-building movement is correctWhether, whether each artis for being concentrated mainly on body builder is located at correct position, so using the sensor on fitness equipment comeJudge that the movement of body builder will generate very big error, just correct labeling and can not show the malfunction of body builder.
Present body-building equipment is designed primarily directed to all non-physical disabilities, but the disabled also has the need of body-building in lifeIt asks.Design scheme in intelligent body-building system scheme for physical disabilities is fewer and fewer, such as Publication No. CN105963956AFull crowd's intelligent body-building system does not relate to individuals with disabilities designed by all ages crowd just for the non-disabled, instituteIt is problem to be solved with the body-building system for individuals with disabilities.
Summary of the invention
It is provided by the invention that the body-building movement error correction system that more crowds are applicable in is acquired based on movement, voice and figure can be passed throughIt reminds body builder's specification to act as the mode of prompting, some body-building is made to act non-type people, it can be in the feelings that do not trainTimely discovery is wrong under condition and corrects, and the body-building of body builder is made to act and can get a desired effect very well;Make in societySome physical disabilities experience the love of society.
The technical solution of the present invention is as follows:
A kind of body-building movement error correction system based on movement acquisition, including movement acquisition device, DSP processing unit, displayDevice and voice prompt device;
Movement acquisition device includes image capture module and data converter, and image capture module shoots strong from different perspectivesThe video image of the body-building movement of body person, data converter are converted to the image data that image capture module acquires comprising human bodyThe digital signal of the two-dimensional coordinate of each key point is simultaneously sent to DSP processing unit;
Dsp processor includes MCU, memory, and memory is stored with a plurality of instruction, and MCU is for recording and executing memoryThe instructions of storage:
The body-building movement of the standardized human body's three-dimensional framework model stored in control display playout storage;
The three-dimensional coordinate of key point is calculated according to the digital signal of the two-dimensional coordinate comprising each key point of human body;
The human body three-dimensional of body builder is established according to the three-dimensional coordinate of each key point of body builder of movement acquisition device outputSkeleton pattern;
The standardized human body's three-dimensional framework mould that will be stored in the body-building movement of the human body three-dimensional skeleton pattern of foundation and memoryThe body-building movement of type is compared, to determine that whether in error range movement and the standard body-building of body builder act: if body-buildingThe activities of person are more than error range, corresponding key point on the human body three-dimensional skeleton pattern of the standard played over the displayIt is highlighted, and/or voice prompting is carried out by voice prompt device.
The above-mentioned body-building based on movement acquisition acts error correction system, wherein the voice prompt device has at least twoA loudspeaker;
An at least loudspeaker is used to play the voice prompting of the body-building movement of corresponding standardized human body's three-dimensional framework model, if strongThe activities of body person's key point are more than error range, and it is dynamic to broadcast position corresponding to this key point by remaining loudspeakerMake the voice prompting of mistake.
The above-mentioned body-building based on movement acquisition acts error correction system, wherein movement acquisition device includes two CCD camera shootingsMachine and two video a/d converters;
CCD camera is placed at the different perspectives in body-building region of body builder, to shoot body builder's different angle simultaneouslyBody-building movement;
The image that each CCD camera takes is switched to the laggard row information of electric signal and handles to obtain by each video a/d converterThe two-dimensional coordinate of each key point of human body.
The above-mentioned body-building based on movement acquisition acts error correction system, wherein the body builder in body-building region takes the photograph in two CCDProjection ray on camera imaging surface intersects at a point in the sky.
The above-mentioned body-building based on movement acquisition acts error correction system, wherein CCD camera is carried out by support triangle frameFixed, the height of the support triangle frame is adjustable, and is furnished with level meter on the turntable of support triangle frame.
The above-mentioned body-building based on movement acquisition acts error correction system, wherein strong at least through movement acquisition device acquisitionThe malfunction of N number of each position maximum magnitude of movement, records each position three-dimensional coordinate most according to malfunction in body movementBig value and minimum value, export to dsp processor, all sites maximum angle data and minimum angles are calculated in dsp processorData;
After the maximum and minimum value of all people's body region is tested out, according to the sequence of storage standard operation, deposit2N array is stored up into memory, the max value of error of each key point of whole body and most when each array respectively represents some movementSmall value, the data in the 2N array are used to judge whether the body-building movement of body builder to be more than error range;N is positive integer.
The present invention also provides a kind of body-building based on movement acquisition to act error correction method simultaneously, includes the following steps:
The body-building movement of playing standard human body three-dimensional skeleton pattern over the display;
Acquire the image that body builder acts in the body-building of different perspectives;
The body-building image for the body builder that different perspectives takes is switched into the laggard row information processing of digital signal, obtains body-buildingThe two-dimensional coordinate of each key point of person, and calculate the three-dimensional coordinate of each key point of body builder;
The human body three-dimensional skeleton pattern of body builder is established according to the three-dimensional coordinate of each key point of body builder;
The body-building movement of the human body three-dimensional skeleton pattern of foundation and the body-building of the human body three-dimensional skeleton pattern of standard are actedIt is compared, to determine that whether in error range movement and the standard body-building of body builder act: if the activities of body builderMore than error range, user is reminded to be corrected at least through the mode that voice reminder and/or display are reminded.
The above-mentioned body-building based on movement acquisition acts error correction method, wherein if the activities of body builder are more than errorRange, corresponding key point is highlighted on the human body three-dimensional skeleton pattern of the standard played over the display.
The above-mentioned body-building based on movement acquisition acts error correction method, wherein the method also includes:
The voice prompting of the body-building movement of corresponding standardized human body's three-dimensional framework model is played by loudspeaker, and
If the activities of body builder's key point are more than error range, this key point institute is broadcasted by remaining loudspeakerThe voice prompting of corresponding position stroke defect.
The above-mentioned body-building based on movement acquisition acts error correction method, wherein the method also includes:
The malfunction for prerecording N number of each position maximum magnitude of movement in body-building movement, according to corresponding to malfunctionThe maximum angle and minimum angles at position obtain the number of the maximum value and minimum value of each position three-dimensional coordinate when malfunctionAccording to;
After the maximum and minimum value of all people's body region is tested out, according to the sequence of storage standard operation, depositStore up 2N array, the max value of error and minimum value of each key point of whole body, the 2N when each array respectively represents some movementData in a array are used to judge whether the body-building movement of body builder to be more than error range;N is positive integer.
The human skeleton threedimensional model of standard operation is completed in invention by software programming.The number of the key point of standard operationAccording to from body builder act in the data of key point that acquire constantly compared, to identify the mistake of body builder's body-building movementAccidentally position carries out color mark to error location on a display screen, while carrying out the position of voice broadcast mistake, makes body-building in this wayPerson is apparent from the mistake of oneself, reduces error brought by sensor;Voice broadcast function and image display function are with regard to appropriateIt is kind solve the problems, such as physical disabilities in stroke defect can error correction in time this, while also making this set body-building system more peopleProperty, it is intelligent.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior artNeeded in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention someEmbodiment for those of ordinary skill in the art without any creative labor, can also be according to theseAttached drawing obtains other attached drawings.
Fig. 1 is that a kind of human action that the present invention provides in one embodiment acquires CCD camera placement schematic diagram;
Fig. 2 is human body corresponding to the human body key point of the invention provided in one embodiment;
Fig. 3 is the simplified diagram that a kind of body-building based on movement acquisition provided by the invention acts error correction system;
Fig. 4 is the flow chart that a kind of camera calibration provided by the invention obtains human body key point three-dimensional coordinate;
Fig. 5 is the work that a kind of body-building based on movement acquisition that the present invention provides in one embodiment acts error correction methodFlow chart.
Specific embodiment
In the following description, a large amount of concrete details are given so as to provide a more thorough understanding of the present invention.SoAnd it is obvious to the skilled person that the present invention may not need one or more of these details and be able toImplement.In other examples, in order to avoid confusion with the present invention, for some technical characteristics well known in the art not intoRow description.
In order to thoroughly understand the present invention, detailed step and detailed structure will be proposed in following description, so as toIllustrate technical solution of the present invention.Presently preferred embodiments of the present invention is described in detail as follows, however other than these detailed descriptions, thisInvention can also have other embodiments.
The present invention provides a kind of body-building based on movement acquisition to act error correction system, referring to shown in Fig. 3-4, includingAct acquisition device, DSP processing unit, display and voice prompt device;
Movement acquisition device includes image capture module and data converter, and image capture module shoots strong from different perspectivesThe video image of the body-building movement of body person, data converter are converted to the image data that image capture module acquires comprising human bodyThe digital signal of the two-dimensional coordinate of each key point is simultaneously sent to DSP processing unit;
Dsp processor includes MCU, memory, and memory is stored with a plurality of instruction, and MCU is for recording and executing memoryThe instructions of storage:
The body-building movement of the standardized human body's three-dimensional framework model stored in control display playout storage;
The three-dimensional coordinate of key point is calculated according to the digital signal of the two-dimensional coordinate comprising each key point of human body;
The human body three-dimensional of body builder is established according to the three-dimensional coordinate of each key point of body builder of movement acquisition device outputSkeleton pattern;
The standardized human body's three-dimensional framework mould that will be stored in the body-building movement of the human body three-dimensional skeleton pattern of foundation and memoryThe body-building movement of type is compared, to determine that whether in error range movement and the standard body-building of body builder act: if body-buildingThe activities of person are more than error range, corresponding key point on the human body three-dimensional skeleton pattern of the standard played over the displayIt is highlighted, and/or voice prompting is carried out by voice prompt device.
Wherein, Software Development Tools used in D reconstruction is the open source computer vision generation that Intel Company establishesThe code library Open CV and Visual C++6.0 run under Microsoft's Windows operating system, and programmed using C/C++Method is realized, the binary digit signal for acting acquisition device output is converted to three-dimensional coordinate data.
Human body three-dimensional skeleton pattern is established to calculate using the particle filter target following of the multiple features fusion based on binocular visionMethod tracks artis position, realizes the target of the final three-dimensional motion skeleton for restoring human body.
Wherein, it can allow coach after completing each movement more to stop in the crucial point data acquisition for carrying out standard operationStay 3-5 seconds time, on the one hand, allow body builder to there is time enough to keep the movement, if the on the other hand body-building of body builderActing wrong can also timely correct.After the body-building movement of acquisition standard, the data of acquisition are stored into memory.
In an optional embodiment of the invention, the voice prompt device has at least two loudspeakers;At least one raisesSound device is used to play the voice prompting of the body-building movement of corresponding standardized human body's three-dimensional framework model, if the office of body builder's key pointPortion's movement is more than error range, is mentioned by the voice that remaining loudspeaker broadcasts position stroke defect corresponding to this key pointShow.This need to be acted when each movement carries out the data acquisition of key point and carry out voice broadcast, explain each movementMain points, and storage of recording, play simultaneously for first loudspeaker and display;For position corresponding to each key pointAlso voice broadcast of the storage for second loudspeaker of specially recording is needed.
In an optional embodiment of the invention, movement acquisition device includes that two CCD cameras and two video a/ds turnParallel operation;Each CCD camera is placed at the different perspectives in body-building region of body builder, to shoot body builder's different angle simultaneouslyBody-building movement, as shown in Figure 1;Each video a/d converter carries out letter after the image that each CCD camera takes is switched to electric signalBreath handles to obtain the two-dimensional coordinate of each key point of human body.Further alternative, the body builder in body-building region is in two CCD camerasProjection ray on imaging surface intersects at a point in the sky.
In an optional embodiment of the invention, CCD camera is fixed by support triangle frame, the support triangleThe height of frame is adjustable, and is furnished with level meter on the turntable of support triangle frame.
In an optional embodiment of the invention, N number of each position of movement in body-building movement is acquired by movement acquisition deviceThe malfunction of maximum magnitude is simultaneously sent to dsp processor, the maximum angle at dsp processor position according to corresponding to malfunctionAnd minimum angles, obtain the maximum value and minimum value of each position three-dimensional coordinate when malfunction;
After the maximum and minimum value of all people's body region is tested out, according to the sequence of storage standard operation, deposit2N array is stored up into memory, the max value of error of each key point of whole body and most when each array respectively represents some movementSmall value, the data in the 2N array are used to judge whether the body-building movement of body builder to be more than error range;N is positive integer.
Wherein, it is as follows accurately to determine the whether standard compliant method of the movement of body builder at this time:
According to the actual conditions that the set body-building acts, each position maximum magnitude in set body-building movement is made by coachMalfunction, such as: the maximum angle of ancon, the smallest angle.The maximum value and minimum of the ancon three-dimensional coordinate of record at this timeThen value uses the method, the data of each movement all sites maximum angle data and minimum angles are obtained, when allPosition maximum and minimum value all test out after, from head, neck, left shoulder, right shoulder, chest, left elbow, right elbow, left wrist,Right wrist, abdomen, left stern, right stern, left knee, right knee, left ankle, right ankle, as shown in Fig. 2, being sequentially stored into according to crucial dot sequency to oneIn a array, if there is N number of movement, then 2N array is stored, respectively represents the mistake of whole body each key point when doing some movementPoor maximum value and minimum value, the data in this 2N array are used for the criterion of error determination module, in this, as body builderError term of reference.
When body builder when carrying out body-building all key points three of each movement obtained by movement acquisition moduleDimension coordinate and error range are constantly compared.Determine whether the movement of body builder at this time complies with standard to realize.
The data of key point at this time are judged not in error range, then dsp processor will issue the positionAlarm signal carries out the transmission of signal by USB communication interface, when voice prompt device receives the signal at different positions,The casting of corresponding information (such as remind: your hand motion is lack of standardization) is made, can inform the malfunction of body builderPosition, while the signal is also communicated to display, when display receives the signal, according to different signals being played onThe key point that red highlights mistake is carried out on three-dimensional framework model;All body builders are facilitated clearly to see which position notComply with standard (such as in hand region red display).
Wherein, the method for being embodied as more crowds' offer guidances is as follows:
By way of voice prompting and/or display prompts, people that whether hearing has obstacle or eyesight to have obstacleIt can clearly prompt whether body builder's body-building movement standardizes, and in the time of the 3-5 second reserve when movement acquisitionIt can just be used to act for body builder's correction.
The explanation of each movement of first loudspeaker in voice prompt device and display show the people of standardThe body-building movement that body three-dimensional framework body-building model is done is synchronous to be carried out, and it is careful that the further body builder for disability crowd providesGuidance, so that it may realize the body builder of different crowd in the case where no coach by display and voice prompt deviceOneself can right a wrong movement, to achieve the purpose that correct body-building.
In the present invention, it is display immediately ahead of body builder, plays the human skeleton three-dimensional mould of the standard builtType body-building movement, body builder can follow the skeleton pattern to learn together, are progressive, so that the movement of body builder more standardizes, reachingTo better body-building effect.
Embodiment two
The present invention also provides a kind of body-building based on movement acquisition to act error correction method simultaneously, includes the following steps:
The body-building movement of playing standard human body three-dimensional skeleton pattern over the display;
Acquire the image that body builder acts in the body-building of different perspectives;
The body-building image for the body builder that different perspectives takes is switched into the laggard row information processing of digital signal, obtains body-buildingThe two-dimensional coordinate of each key point of person, and calculate the three-dimensional coordinate of each key point of body builder;
The human body three-dimensional skeleton pattern of body builder is established according to the three-dimensional coordinate of each key point of body builder;
The body-building movement of the human body three-dimensional skeleton pattern of foundation and the body-building of the human body three-dimensional skeleton pattern of standard are actedIt is compared, to determine that whether in error range movement and the standard body-building of body builder act: if the activities of body builderMore than error range, user is reminded to be corrected at least through the mode that voice reminder and/or display are reminded.
In an optional embodiment of the invention, if the activities of body builder are more than error range, broadcast over the displayCorresponding key point is highlighted on the human body three-dimensional skeleton pattern for the standard put.
In an optional embodiment of the invention, the method also includes:
The voice prompting of the body-building movement of corresponding standardized human body's three-dimensional framework model is played by loudspeaker, and
If the activities of body builder's key point are more than error range, this key point institute is broadcasted by remaining loudspeakerThe voice prompting of corresponding position stroke defect.
In an optional embodiment of the invention, the method also includes:
The malfunction for prerecording N number of each position maximum magnitude of movement in body-building movement, according to corresponding to malfunctionThe maximum angle and minimum angles at position obtain the number of the maximum value and minimum value of each position three-dimensional coordinate when malfunctionAccording to;
After the maximum and minimum value of all people's body region is tested out, according to the sequence of storage standard operation, depositStore up 2N array, the max value of error and minimum value of each key point of whole body, the 2N when each array respectively represents some movementData in a array are used to judge whether the body-building movement of body builder to be more than error range;Wherein, N is positive integer.
In conclusion due to present invention employs above-mentioned technical solution, study course and the guidance for realizing body-building movement are wrongBody-building movement accidentally, the malfunction of body builder can be rapidly determined in body-building and carries out phonetic warning, to standardizeThe body-building of body builder acts, to reach expected body-building effect.
Presently preferred embodiments of the present invention is described above.It is to be appreciated that the invention is not limited to above-mentionedParticular implementation, devices and structures not described in detail herein should be understood as gives reality with the common mode in this fieldIt applies;Anyone skilled in the art, without departing from the scope of the technical proposal of the invention, all using the disclosure aboveMethods and technical content many possible changes and modifications are made to technical solution of the present invention, or be revised as equivalent variations etc.Embodiment is imitated, this is not affected the essence of the present invention.Therefore, anything that does not depart from the technical scheme of the invention, foundationTechnical spirit of the invention any simple modifications, equivalents, and modifications made to the above embodiment, still fall within the present inventionIn the range of technical solution protection.

Claims (7)

CN201710346230.7A2017-05-172017-05-17A kind of body-building movement error correction system and method based on movement acquisitionExpired - Fee RelatedCN107050774B (en)

Priority Applications (1)

Application NumberPriority DateFiling DateTitle
CN201710346230.7ACN107050774B (en)2017-05-172017-05-17A kind of body-building movement error correction system and method based on movement acquisition

Applications Claiming Priority (1)

Application NumberPriority DateFiling DateTitle
CN201710346230.7ACN107050774B (en)2017-05-172017-05-17A kind of body-building movement error correction system and method based on movement acquisition

Publications (2)

Publication NumberPublication Date
CN107050774A CN107050774A (en)2017-08-18
CN107050774Btrue CN107050774B (en)2019-04-16

Family

ID=59610785

Family Applications (1)

Application NumberTitlePriority DateFiling Date
CN201710346230.7AExpired - Fee RelatedCN107050774B (en)2017-05-172017-05-17A kind of body-building movement error correction system and method based on movement acquisition

Country Status (1)

CountryLink
CN (1)CN107050774B (en)

Families Citing this family (37)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN108205654B (en)*2017-09-302021-06-04北京市商汤科技开发有限公司Action detection method and device based on video
CN107767930A (en)*2017-10-132018-03-06广东工业大学A kind of smart motion bearing calibration, device and equipment
CN107833283A (en)*2017-10-302018-03-23努比亚技术有限公司A kind of teaching method and mobile terminal
CN107886075B (en)*2017-11-132019-08-16广东工业大学A kind of method and device of body-building motion detection
CN107694050B (en)*2017-11-132019-08-16广东工业大学A kind of intelligent body-building tool
CN108211312A (en)*2017-11-302018-06-29中国联合网络通信集团有限公司The action correction method and apparatus moved based on AR or VR
CN110298221B (en)*2018-03-232022-02-11上海史贝斯健身管理有限公司Self-help fitness method and system, electronic equipment and storage medium
CN108734104B (en)*2018-04-202021-04-13杭州易舞科技有限公司Body-building action error correction method and system based on deep learning image recognition
CN108905164A (en)*2018-05-292018-11-30广东工业大学A kind of donning system for correcting athletic posture
CN109144247A (en)*2018-07-172019-01-04尚晟The method of video interactive and based on can interactive video motion assistant system
EP3833455B1 (en)*2018-08-072025-07-09Interactive Strength, Inc.Interactive exercise machine data architecture
CN109145814A (en)*2018-08-202019-01-04贺州学院safety evaluation method and device
CN109344706A (en)*2018-08-282019-02-15杭州电子科技大学 A method for obtaining photos of special human body poses that can be operated by one person
CN109222909B (en)*2018-09-302022-11-08李莉Wearable intelligent monitoring device and method for monitoring motion, spine bending and joint wear
CN109635925A (en)*2018-11-302019-04-16北京首钢自动化信息技术有限公司A kind of sportsman's supplemental training data capture method, device and electronic equipment
CN109731278A (en)*2018-12-122019-05-10北京小米移动软件有限公司 Data processing method and device, pen body, electronic device and readable storage medium
CN111460868A (en)*2019-01-222020-07-28上海形趣信息科技有限公司Action recognition error correction method, system, electronic device and storage medium
CN109934111B (en)*2019-02-122020-11-24清华大学深圳研究生院Fitness posture estimation method and system based on key points
CN112237730B (en)*2019-07-172022-12-27腾讯科技(深圳)有限公司Body-building action correcting method and electronic equipment
CN110718280A (en)*2019-09-262020-01-21北京金山安全软件有限公司Fitness action accuracy determining method and device, electronic equipment and storage medium
CN110782482A (en)*2019-10-212020-02-11深圳市网心科技有限公司 Exercise evaluation method, device, computer equipment and storage medium
CN111111111B (en)*2020-01-142023-06-23广东技术师范大学 A real-time fitness monitoring system and method
CN111514560A (en)*2020-04-072020-08-11广州体育学院Volleyball detection system capable of identifying athletes
CN113534943B (en)*2020-04-132025-05-09华为技术有限公司 A method and device for judging fitness venue
CN111639605B (en)*2020-06-012024-04-26影子江湖文化(北京)有限公司Human body action scoring method based on machine vision
CN111790103B (en)*2020-06-102021-09-28湖南工商大学Aerobics exercises shape training correction device and correction method
CN112464918B (en)*2021-01-272021-06-25昆山恒巨电子有限公司Body-building action correcting method and device, computer equipment and storage medium
CN115147339B (en)*2021-03-312025-08-08华为技术有限公司 Human body key point detection method and related device
CN113096152B (en)*2021-04-292022-04-01北京百度网讯科技有限公司 Multi-object motion analysis method, apparatus, device and medium
CN113033526A (en)*2021-05-272021-06-25北京欧应信息技术有限公司Computer-implemented method, electronic device and computer program product
CN115641355A (en)*2021-07-202023-01-24北京百度网讯科技有限公司 Method, device, device, medium and product for detecting skeletons
CN113573152B (en)*2021-07-222024-01-26广州艾美网络科技有限公司Motion sensing entertainment device
CN114035683B (en)*2021-11-082024-03-29百度在线网络技术(北京)有限公司User capturing method, apparatus, device, storage medium and computer program product
CN114267085A (en)*2021-12-302022-04-01广东中科凯泽信息科技有限公司 How to use 3D human motion analysis system based on AI technology
CN114356100B (en)*2022-01-132024-05-07上海健指树智能系统有限公司Body-building action guiding method, body-building action guiding device, electronic equipment and storage medium
CN114334084B (en)*2022-03-012022-06-24深圳市海清视讯科技有限公司Body-building data processing method, device, equipment and storage medium
CN114400067A (en)*2022-03-022022-04-26国家体育总局体育科学研究所Artificial intelligence body-building guidance system based on visual transmission and device thereof

Citations (5)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN101202994A (en)*2006-12-142008-06-18北京三星通信技术研究有限公司 Method and device for assisting user in fitness
CN101840587A (en)*2009-03-172010-09-22三星电子株式会社Apparatus and method for generating skeleton model using motion data and image data
CN104200491A (en)*2014-08-152014-12-10浙江省新华医院Motion posture correcting system for human body
CN105597282A (en)*2015-12-172016-05-25安徽寰智信息科技股份有限公司Method and system for correcting body building motions
US9744426B2 (en)*2015-06-262017-08-29Hon Hai Precision Industry Co., Ltd.Electronic device and method for controlling the electronic device

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN101202994A (en)*2006-12-142008-06-18北京三星通信技术研究有限公司 Method and device for assisting user in fitness
CN101840587A (en)*2009-03-172010-09-22三星电子株式会社Apparatus and method for generating skeleton model using motion data and image data
CN104200491A (en)*2014-08-152014-12-10浙江省新华医院Motion posture correcting system for human body
US9744426B2 (en)*2015-06-262017-08-29Hon Hai Precision Industry Co., Ltd.Electronic device and method for controlling the electronic device
CN105597282A (en)*2015-12-172016-05-25安徽寰智信息科技股份有限公司Method and system for correcting body building motions

Also Published As

Publication numberPublication date
CN107050774A (en)2017-08-18

Similar Documents

PublicationPublication DateTitle
CN107050774B (en)A kind of body-building movement error correction system and method based on movement acquisition
CN109815907B (en)Sit-up posture detection and guidance method based on computer vision technology
CN103706106B (en)A kind of self adaptation continuous action training method based on Kinect
CN109011508A (en)A kind of intelligent coach system and method
CN104200491A (en)Motion posture correcting system for human body
US9418470B2 (en)Method and system for selecting the viewing configuration of a rendered figure
CN106409030A (en)Customized foreign spoken language learning system
CN107281710A (en)A kind of method of remedial action error
CN106710341A (en)Education training management system
Baran et al.Design of a home-based adaptive mixed reality rehabilitation system for stroke survivors
WO2018214520A1 (en)Method and apparatus for synchronizing video data and exercise effect animation
CN107050803A (en)A kind of shuttlecock training supervision assessment system
CN118627519B (en)Digital person construction method and system based on multi-mode large model
CN104484574A (en)Real-time human body gesture supervised training correction system based on quaternion
CN109545003A (en)A kind of display methods, device, terminal device and storage medium
WO2023077660A1 (en)Tai chi training method and system based on mixed reality, device, and storage medium
Huang et al.Miss yoga: a yoga assistant mobile application based on keypoint detection
CN119649997B (en) Fitness guidance system and method based on AI posture analysis and MR human-computer interaction
CN116510271A (en) A Taijiquan Intelligent Auxiliary Training and Evaluation System
CN104933278B (en)A kind of multi-modal interaction method and system for disfluency rehabilitation training
CN110314344A (en)Move based reminding method, apparatus and system
CN111986260A (en)Image processing method and device and terminal equipment
CN117437676A (en)Method, device, equipment and medium for driving half body based on StyleGAN
Bourbakis et al.A 2D vibration array for sensing dynamic changes and 3D space for Blinds' navigation
CN113283402B (en)Differential two-dimensional fixation point detection method and device

Legal Events

DateCodeTitleDescription
PB01Publication
PB01Publication
SE01Entry into force of request for substantive examination
SE01Entry into force of request for substantive examination
GR01Patent grant
GR01Patent grant
CF01Termination of patent right due to non-payment of annual fee
CF01Termination of patent right due to non-payment of annual fee

Granted publication date:20190416


[8]ページ先頭

©2009-2025 Movatter.jp