CN104200491A - Motion posture correcting system for human body - Google Patents
Motion posture correcting system for human body Download PDFInfo
- Publication number
- CN104200491A CN104200491A CN201410401905.XA CN201410401905A CN104200491A CN 104200491 A CN104200491 A CN 104200491A CN 201410401905 A CN201410401905 A CN 201410401905A CN 104200491 A CN104200491 A CN 104200491A
- Authority
- CN
- China
- Prior art keywords
- image
- data
- standard
- human
- human body
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention relates to a motion posture correcting system for a human body. The system comprises an image collecting module, an image standard library module, an image comparing module and an image correcting output module, wherein the image collecting module adopts a kinect camera to collect a human body image with depth information so as to build skeleton data and joint data of the human body; standard motion posture data for the human body are stored in the image standard library module and comprises the skeleton data and the joint data of the human body; skeleton and posture Euclidean distance data of the human body are compared with the standard motion posture data in a standard library by the image comparing module so as to obtain a result whether postures are correct or not, and obtain an error among postures of the human body opposite to correct postures; and the result and the biased information obtained by comparing the collected postures of the human body with the standard postures of the human body in the image standard library are output by the image correcting output module. The motion posture correcting system for the human body can remind for wrong postures of the human body so as to correct practicers' motion.
Description
Technical field
The present invention relates to posture correction system, particularly human motion posture correction system.
Background technology
The current correction to human motion attitude, such as the teaching that move on the basis of teacher's taijiquan, five-animal exercises, golf, tennis etc. sports events, is mainly to adopt the transaudient religion of demonstration movement sound by coach, and coach carries out voice then and there, limbs are proofreaied and correct.This traditional correcting mode, to train individual subjective judgement as benchmark, is difficult to accomplish unified standard.Be limited to self level of coach, such as coach's itself stroke defect or nonstandard, cause student's action learning inaccurate; And the impact of proofreading and correct subjective and objective factors such as being subject to mood at that time of coach, mood, exercise environment then and there, make each standard of proofreading and correct also can be different.The attitude correction of human motion is gone back to the corresponding method that can standard application of neither one at present.
Summary of the invention
The present invention is the problem that solves current human motion attitude correction, and a kind of human motion posture correction system is provided, and this corrective system can remind to make it to correct to wrong human motion attitude.
For achieving the above object, the present invention by the following technical solutions, comprising:
A kind of human motion posture correction system, comprises image collecting module, image java standard library module, image contrast module, adjustment of image output module; Described image collecting module is kinect camera, for gathering the body image with depth information, and the image gathering is analyzed, and builds human skeleton data and human joint points Euclidean distance data, to draw human motion attitude information; In image java standard library module, store human body standard movement attitude data, human body standard movement attitude data comprises human skeleton data and human joint points data; Standard movement attitude data in human skeleton and human joint points Euclidean distance data and java standard library that image contrast module builds kinect camera is compared, draw the result whether attitude is correct, and draw the error between the relatively correct attitude of human body attitude; Adjustment of image output module, by the result of the standard movement attitude contrast in the human body attitude and the image java standard library that gather and control information output.
Above-mentioned a kind of human motion posture correction system, described image contrast module follows these steps to contrast human skeleton and articulation point Euclidean distance data:
The first step, get human body neck, shoulder, elbow, wrist, hip, knee, ankle for contrast node;
Second step, obtain the three-dimensional Euclidean distance data of each node from kinect camera;
The 3rd step, the node data node data and the standard database obtained from kinect camera is compared, with Euclidean distance unit as a comparison;
The 4th step, calculate the error between data and the standard operation data of each action in each time period, calculate the error on the each node of each action;
The 5th step, as error exceeds specialized range, judge in this time period of user that action does not reach standard; Error does not exceed specialized range, represents that the action in user's current slot reaches standard.
Above-mentioned a kind of human motion posture correction system, described error specialized range is 5%.
Above-mentioned a kind of human motion posture correction system, described human joint points is neck, shoulder, elbow, wrist, hip, knee, ankle.
Above-mentioned a kind of human motion posture correction system, described adjustment of image output module comprises demonstration output, at display screen or by projector display standard athletic posture image and the athletic posture image collecting on projection screen, show two kinds of images with different color, and show wrong node.
Above-mentioned a kind of human motion posture correction system, described athletic posture image shows with human body contour outline or human skeleton shows.
Above-mentioned a kind of human motion posture correction system, described adjustment of image output module also comprises voice output.
Above-mentioned a kind of human motion posture correction system, the human body standard movement attitude data of storing in image java standard library module, is to obtain by kinect camera collection standard movement attitude.
Above-mentioned a kind of human motion posture correction system, kinect camera carries out in the following manner to the collection of standard movement attitude: can do the teacher of standard operation to each, each action need gather above attitude data 3 times, gather altogether 10 teachers' data, these data are averaged and generated athletic posture normal data.
The present invention is by having the kinect camera collection person's of practising who gathers image depth information three-dimensional motion attitude, it and the standard movement attitude in standard database are compared, in the time of the person's of practising stroke defect, show with voice reminder and point out by demonstration, make the person of practising depart from trainer, reach the object of training standard action.
Kinect is the name that Microsoft formally issued XBOX360 body sense periphery peripheral hardware on June 14th, 2010." Kinect " is kinetics(dynamics) add that connection(connects) new term that two words are created certainly, pronunciation is con-nect(/k n'kt/), be not ki-nect(/k n'kt/) or Kir-nect.
What Kinect camera used is a kind of light coding (light coding) technology.Be different from traditional ToF or structural light measurement technology, what light coding used is continuous illumination (and non-pulse), does not also need special sensitive chip, and only needs common CMOS sensitive chip, and this allows the cost of scheme greatly reduce.
Kinect has three cameras, and middle camera lens is RGB colour TV camera, and the right and left camera lens is respectively infrared transmitter and infrared C MOS video camera.In addition, kinect has also arranged in pairs or groups and has chased after burnt technology, and base motor can rotate along with the movement of focusing object.
Light coding, as the term suggests be exactly to needing the space of measuring to be numbered with code, after all or structured light technique with light illumination.But different from traditional method of structured light, what his light source got out is not the two-dimentional Image Coding that a secondary period property changes, but one has " the body coding " of three-dimensional depth.This light source is called laser speckle (laser speckle), is the random diffraction spot forming to rough object or after penetrating frosted glass when Ear Mucosa Treated by He Ne Laser Irradiation.
These speckles have the randomness of height, and can be along with the different changing patterns of distance.The speckle pattern that is to say any two places in space is all different.As long as stamp such structured light in space, mark has just all been done in whole space, and an object is put into this space, as long as look at the speckle pattern above object, just can know where this object is.Certainly, the speckle pattern in whole space all to be recorded before this, so will first do the demarcation of primary source.The method of demarcating is such: every a segment distance, get reference planes, the speckle pattern in reference planes is recorded.Suppose that User Activity space is the scope apart from 1 meter to 4 meters of kinect camera, get reference planes every 10cm, demarcate so us and just preserved 30 width speckle images.When need to measuring, take the speckle image of a secondary scene to be measured, this width image and the 30 width reference pictures that we preserve are taken turns doing to computing cross-correlation, we can obtain 30 width degree of correlation images like this, and the position that has object to exist in space will demonstrate peak value on degree of correlation image.These peak values are stacked from level to level, then pass through some interpolation, will obtain the 3D shape of whole scene.
Microsoft provides SDK(Software Development Kit for kinect) be the development interface of SDK (Software Development Kit) as kinect camera, its main characteristics comprises:
Original sense data stream: developer can directly obtain the original data stream of range sensor, colour camera and four unit microphone arrays.These data allow developer can utilize the low order data stream of Kinect sensor for carrying out application development in basis.
Skeleton is followed the trail of: this cover SDK can follow the trail of the skeleton image of one or two user in the Kinect visual field, is convenient to set up the application program with body sense operation.
The present invention carries out secondary development on the basis of the SDK of kinect, the framework information obtaining is utilized, to proofread and correct human motion attitude by kinect camera.
Brief description of the drawings
Fig. 1 is the demonstration schematic diagram of the embodiment of the present invention one human body attitude time up to standard.
Fig. 2 is the demonstration schematic diagram of the embodiment of the present invention one human body attitude when below standard.
Fig. 3 is the structure principle chart of human body image acquisition device kinect camera of the present invention.
Fig. 4 is the process flow diagram that human body image of the present invention gathers.
Fig. 5 is the process flow diagram of human body image contrast of the present invention.
In figure, be labeled as: 1 infrared transmitter, 2 infrared C MOS cameras, 3RGB colour imagery shot, 4 flash memories, 5USB interface, 6 crystal oscillators, 7 external digital sound sources, 8 microphones.
Embodiment
With reference to accompanying drawing, a kind of human motion posture correction system, comprises image collecting module, image java standard library module, image contrast module, adjustment of image output module.
Described image collecting module is kinect camera, the data of obtaining comprise the three dimensions depth information at each position on the coloured image of sporter's human body and health, build the three-dimensional data of human skeleton data and the each articulation point of human body, to draw human motion attitude information.
In image java standard library module, store human body standard movement attitude data.
Utilize kinect camera as image collecting module, gather the movement sequence data that meet motion specification, form athletic posture standard database, go forward side by side line item and preservation.Described exercise data comprises: a complete set of motion digital video image that meets specification.
Image collecting module need meet the collection of carrying out data under specific environment scene, has enough ambient lightings and brightness, can clearly obtain motion image.
The data that adopt this image collecting module to obtain are obtained the three dimensions depth information of each point on the coloured image of sporter's human body and health simultaneously.By these information, can further calculate and obtain the limbs attitude information of movement human in three dimensions.Wherein, common color camera is for obtaining the color image information of movement human, and infrared transmitter and receiver can obtain the depth information of partes corporis humani position in three dimensions.For the accuracy that ensures that normal data gathers, to each standard compliant motion people, each action needs to gather above attitude data 3 times, gathers altogether 10 sporters' data, these data are averaged to generate athletic posture normal data, and set up human body standard movement attitude data storehouse.
No matter be collection standard human motion attitude data, or gather the person's of practising athletic posture data, all need to calculate the exercise data of main articulation point, and then obtain the critical movements data of human body attitude, could be in order to contrast and analysis.Calculation procedure is as follows:
1) obtain skeleton information: obtain respectively image information and the depth information about human body by this image collecting module of kinect camera, calculate human skeleton information according to these information, comprise mark and the three-dimensional coordinate data in bone position, joint.According to the skeleton diagram of these Information generations, be movement locus coupling and the basis of proofreading and correct.
2) choose main joint: for improving accuracy and the service efficiency of attitude information and movement locus coupling, choose neck, shoulder, elbow, wrist, hip, knee, ankle-joint, using these joints as attitude information key node, record respectively each joint position three-dimensional coordinate data, calculate position and the attitude information of other articulation points of human body according to these data.
Image contrast module:
1) for each key operations node that needs coupling, the 3 d pose data of the articulation point to the person of practising who obtains are compared with the data of corresponding key node in normal data, calculate the error between each data and standard operation data of moving in each time period, error represents with point-to-point transmission Euclidean distance.Euclidean distance (Euclidean distance) also claim Euclidean distance, and it is a distance definition conventionally adopting, and it is the actual distance between two points in m-dimensional space.
2), for moving in every period, system, according to action norm requirement, calculates different error range on the each key node of each action.
3) the three-dimensional data normal data user who obtains being moved in crucial articulation point is compared, and as error exceeds specialized range, judges that in this time period of user, action fails to reach standard; Error does not exceed specialized range, and in this example, error range is defined as 5%, represents that the action in user's current slot reaches standard.
Human motion attitude correction output module:
Native system is exported with two kinds of method prompting users of voice message and is carried out the correction of athletic posture simultaneously by display screen.
With reference to accompanying drawing 1 and Fig. 2, right side skeleton is standard attitude skeleton, and left side is the skeleton that the person of practising is sampled to generation.On Fig. 2, can see and have the articulation point highlighting, these articulation points are moved not in place, non-type picture cues exactly.
If user does not reach standard operation, system will highlight the joint of the below standard standard of attitude, and should how to adjust with direction arrow and text prompt on screen, and which direction certain position should move how many distances to.Meanwhile, voice message is carried out in the joint of below standard standard, export related voice by stereo set, how prompting user should adjust, and which kind of direction certain position should move how many distances to.Until its attitude meets the action criteria that system specifies completely.If the This move person of practising, when time not completing through repeatedly making great efforts, also can select to skip, and enters the correction of next action.
User reaches the action of standard, or is reaching action criteria after overcorrect adjustment, can continue to carry out next action.
Claims (9)
1. a human motion posture correction system, is characterized in that:
Comprise image collecting module, image java standard library module, image contrast module, adjustment of image output module; Described image collecting module is kinect camera, for gathering the body image with depth information, and the image gathering is analyzed, and builds human skeleton data and human joint points Euclidean distance data, to draw human motion attitude information; In image java standard library module, store human body standard movement attitude data, human body standard movement attitude data comprises human skeleton data and human joint points data; Standard movement attitude data in human skeleton and human joint points Euclidean distance data and java standard library that image contrast module builds kinect camera is compared, draw the result whether attitude is correct, and draw the error between the relatively correct attitude of human body attitude; Adjustment of image output module, by the result of the standard movement attitude contrast in the human body attitude and the image java standard library that gather and control information output.
2. a kind of human motion posture correction system as claimed in claim 1, is characterized in that described image contrast module follows these steps to contrast human skeleton and articulation point Euclidean distance data:
Get human body neck, shoulder, elbow, wrist, hip, knee, ankle for contrasting node;
Obtain the three-dimensional Euclidean distance data of each node from kinect camera;
Node data node data and the standard database obtained from kinect camera is compared, with Euclidean distance unit as a comparison;
Calculate the error between each data and standard operation data of moving in each time period, calculate the error on the each node of each action;
As error exceeds specialized range, judge that in this time period of user, action does not reach standard; Error does not exceed specialized range, represents that the action in user's current slot reaches standard.
3. a kind of human motion posture correction system as claimed in claim 2, is characterized in that described error specialized range is 5%.
4. a kind of human motion posture correction system as claimed in claim 1, is characterized in that described human joint points is neck, shoulder, elbow, wrist, hip, knee, ankle.
5. a kind of human motion posture correction system as claimed in claim 1, it is characterized in that described adjustment of image output module comprises demonstration output, at display screen or by projector display standard athletic posture image and the athletic posture image collecting on projection screen, show two kinds of images with different color, and show wrong node.
6. a kind of human motion posture correction system as claimed in claim 5, is characterized in that described athletic posture image shows with human body contour outline or human skeleton shows.
7. a kind of human motion posture correction system as claimed in claim 1, is characterized in that described adjustment of image output module also comprises voice output.
8. a kind of human motion posture correction system as claimed in claim 1, is characterized in that the human body standard movement attitude data stored in image java standard library module, is to obtain by kinect camera collection standard movement attitude.
9. a kind of human motion posture correction system as claimed in claim 8, it is characterized in that kinect camera carries out in the following manner to the collection of standard movement attitude: can do the teacher of standard operation to each, each action need gather above attitude data 3 times, gather altogether 10 teachers' data, these data are averaged and generated athletic posture normal data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410401905.XA CN104200491A (en) | 2014-08-15 | 2014-08-15 | Motion posture correcting system for human body |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410401905.XA CN104200491A (en) | 2014-08-15 | 2014-08-15 | Motion posture correcting system for human body |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104200491A true CN104200491A (en) | 2014-12-10 |
Family
ID=52085777
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410401905.XA Pending CN104200491A (en) | 2014-08-15 | 2014-08-15 | Motion posture correcting system for human body |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104200491A (en) |
Cited By (48)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104394386A (en) * | 2014-12-11 | 2015-03-04 | 盐城工学院 | System and method for evaluating knee joint motion normativity through multi-view sequence images |
| CN104486590A (en) * | 2014-12-26 | 2015-04-01 | 安徽寰智信息科技股份有限公司 | Video acquisition and processing method for golf teaching and training |
| CN105196298A (en) * | 2015-10-16 | 2015-12-30 | 费文杰 | Non-contact interaction doll display system and non-contact interaction doll display method |
| CN105307017A (en) * | 2015-11-03 | 2016-02-03 | Tcl集团股份有限公司 | Method and device for correcting posture of smart television user |
| CN105534528A (en) * | 2015-12-08 | 2016-05-04 | 杭州电子科技大学 | Non-contact physical test system and test method based on somatosensory recognition |
| CN105664462A (en) * | 2016-01-07 | 2016-06-15 | 北京邮电大学 | Auxiliary training system based on human body posture estimation algorithm |
| CN105816182A (en) * | 2016-03-24 | 2016-08-03 | 西安交通大学 | Method for measuring cervical vertebra motion degree on basis of Kinect sensor |
| CN105999670A (en) * | 2016-05-31 | 2016-10-12 | 山东科技大学 | Shadow-boxing movement judging and guiding system based on kinect and guiding method adopted by same |
| CN106372294A (en) * | 2016-08-30 | 2017-02-01 | 苏州品诺维新医疗科技有限公司 | Method and device for correcting posture |
| CN106650687A (en) * | 2016-12-30 | 2017-05-10 | 山东大学 | Posture correction method based on depth information and skeleton information |
| CN106923567A (en) * | 2017-04-01 | 2017-07-07 | 浙江陀曼精密机械有限公司 | A kind of intelligent health chair appearance method of data capture |
| CN106974656A (en) * | 2016-01-15 | 2017-07-25 | 赵敏岗 | For gathering motion state and carrying out the system and implementation method of real time contrast's correction |
| CN107050774A (en) * | 2017-05-17 | 2017-08-18 | 上海电机学院 | A kind of body-building action error correction system and method based on action collection |
| CN107469294A (en) * | 2016-06-08 | 2017-12-15 | 上海体育学院 | A kind of paddler's motion analysis system based on KINECT hardware |
| CN107767930A (en) * | 2017-10-13 | 2018-03-06 | 广东工业大学 | A kind of smart motion bearing calibration, device and equipment |
| CN108090394A (en) * | 2016-11-21 | 2018-05-29 | 风跑体育发展（深圳）有限公司 | A kind of running action automatic tracking method and its system |
| CN108211312A (en) * | 2017-11-30 | 2018-06-29 | 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 |
| CN108256433A (en) * | 2017-12-22 | 2018-07-06 | 银河水滴科技（北京）有限公司 | A kind of athletic posture appraisal procedure and system |
| CN108537284A (en) * | 2018-04-13 | 2018-09-14 | 东莞松山湖国际机器人研究院有限公司 | Posture assessment scoring method based on computer vision deep learning algorithm and system |
| CN108542021A (en) * | 2018-03-18 | 2018-09-18 | 江苏特力威信息系统有限公司 | A kind of gym suit and limbs measurement method and device based on vitta identification |
| CN108905164A (en) * | 2018-05-29 | 2018-11-30 | 广东工业大学 | A kind of donning system for correcting athletic posture |
| CN109222909A (en) * | 2018-09-30 | 2019-01-18 | 李莉 | A kind of wearable intelligent monitoring device and the method for monitoring movement, spinal curvature and joint wear |
| CN109274883A (en) * | 2018-07-24 | 2019-01-25 | 广州虎牙信息科技有限公司 | Posture antidote, device, terminal and storage medium |
| WO2019075824A1 (en) * | 2017-10-20 | 2019-04-25 | 深圳市鹰硕技术有限公司 | System for correcting and training running posture of child |
| CN110338806A (en) * | 2019-07-09 | 2019-10-18 | 四川大学华西第二医院 | The correct posture correction system of pregnant woman |
| CN110338807A (en) * | 2019-07-09 | 2019-10-18 | 四川大学华西第二医院 | Pregnant woman's attitude updating and monitoring system |
| CN110353691A (en) * | 2018-04-10 | 2019-10-22 | 仁宝电脑工业股份有限公司 | Act assessment system, its method and non-transient computer-readable recording medium |
| CN110751100A (en) * | 2019-10-22 | 2020-02-04 | 北京理工大学 | Auxiliary training method and system for stadium |
| CN110782482A (en) * | 2019-10-21 | 2020-02-11 | 深圳市网心科技有限公司 | Motion evaluation method and device, computer equipment and storage medium |
| CN110796077A (en) * | 2019-10-29 | 2020-02-14 | 湖北民族大学 | Attitude motion real-time detection and correction method |
| CN110866440A (en) * | 2019-09-27 | 2020-03-06 | 惠州市德赛西威汽车电子股份有限公司 | Pointer instrument deep learning network building method, detection method and system |
| CN111067597A (en) * | 2019-12-10 | 2020-04-28 | 山东大学 | System and method for determining puncture path according to human body posture in tumor puncture |
| CN111359159A (en) * | 2020-03-24 | 2020-07-03 | 成都翡铭科技有限公司 | Cervical vertebra rehabilitation training method |
| CN111460868A (en) * | 2019-01-22 | 2020-07-28 | 上海形趣信息科技有限公司 | Action recognition error correction method, system, electronic device and storage medium |
| CN111803905A (en) * | 2020-06-04 | 2020-10-23 | 上海市东方医院（同济大学附属东方医院） | Parkinson's disease patient muscle activity monitor |
| CN111985443A (en) * | 2020-09-01 | 2020-11-24 | 安徽炬视科技有限公司 | Robust human body posture estimation algorithm |
| CN112422946A (en) * | 2020-11-30 | 2021-02-26 | 重庆邮电大学 | Intelligent yoga action guidance system based on 3D reconstruction |
| CN112487965A (en) * | 2020-11-30 | 2021-03-12 | 重庆邮电大学 | Intelligent fitness action guiding method based on 3D reconstruction |
| CN112668531A (en) * | 2021-01-05 | 2021-04-16 | 重庆大学 | Motion posture correction method based on motion recognition |
| CN112714328A (en) * | 2020-12-23 | 2021-04-27 | 作业帮教育科技（北京）有限公司 | Live course student posture prompting method and device and electronic equipment |
| CN112883808A (en) * | 2021-01-23 | 2021-06-01 | 招商新智科技有限公司 | Method and device for detecting abnormal behavior of pedestrian riding escalator and electronic equipment |
| CN112911393A (en) * | 2018-07-24 | 2021-06-04 | 广州虎牙信息科技有限公司 | Part recognition method, device, terminal and storage medium |
| CN113297876A (en) * | 2020-02-21 | 2021-08-24 | 佛山市云米电器科技有限公司 | Motion posture correction method based on intelligent refrigerator, intelligent refrigerator and storage medium |
| WO2021169223A1 (en) * | 2020-02-24 | 2021-09-02 | 五邑大学 | Learning-type robot, and learning correction method based on same |
| CN113367688A (en) * | 2021-04-28 | 2021-09-10 | 北京理工大学 | Hemiplegia rating method and system based on human body static gait and TOF camera |
| TWI822473B (en) * | 2022-11-18 | 2023-11-11 | 財團法人資訊工業策進會 | Method, processing control device and system of providing movement improvement information |
| CN117078885A (en) * | 2023-09-07 | 2023-11-17 | 广州市创佳建筑模型有限公司 | Building model spliced sand table coordinate and posture guiding system based on feature recognition |
| CN117558457A (en) * | 2024-01-11 | 2024-02-13 | 合肥特斯塔信息科技有限公司 | Customer portrait analysis method in customer relationship management system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101655990A (en) * | 2009-06-25 | 2010-02-24 | 浙江大学 | Method for synthesizing three-dimensional human body movement based on non-linearity manifold study |
| CN102622603A (en) * | 2011-01-31 | 2012-08-01 | 索尼公司 | Method and apparatus for evaluating human pose recognition technology |
| CN102663779A (en) * | 2012-05-03 | 2012-09-12 | 西安电子科技大学 | Human motion tracking method based on stochastic Gaussian hidden variables |
| CN102682452A (en) * | 2012-04-12 | 2012-09-19 | 西安电子科技大学 | Human movement tracking method based on combination of production and discriminant |
| CN102982315A (en) * | 2012-11-05 | 2013-03-20 | 中国科学院计算技术研究所 | Gesture segmentation recognition method capable of detecting non-gesture modes automatically and gesture segmentation recognition system |
| CN103198297A (en) * | 2013-03-15 | 2013-07-10 | 浙江大学 | Kinematic similarity assessment method based on correlation geometrical characteristics |
| CN103839040A (en) * | 2012-11-27 | 2014-06-04 | 株式会社理光 | Gesture identification method and device based on depth images |
| WO2014113507A1 (en) * | 2013-01-15 | 2014-07-24 | Leap Motion, Inc. | Dynamic user interactions for display control and customized gesture interpretation |
-
2014
- 2014-08-15 CN CN201410401905.XA patent/CN104200491A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101655990A (en) * | 2009-06-25 | 2010-02-24 | 浙江大学 | Method for synthesizing three-dimensional human body movement based on non-linearity manifold study |
| CN102622603A (en) * | 2011-01-31 | 2012-08-01 | 索尼公司 | Method and apparatus for evaluating human pose recognition technology |
| CN102682452A (en) * | 2012-04-12 | 2012-09-19 | 西安电子科技大学 | Human movement tracking method based on combination of production and discriminant |
| CN102663779A (en) * | 2012-05-03 | 2012-09-12 | 西安电子科技大学 | Human motion tracking method based on stochastic Gaussian hidden variables |
| CN102982315A (en) * | 2012-11-05 | 2013-03-20 | 中国科学院计算技术研究所 | Gesture segmentation recognition method capable of detecting non-gesture modes automatically and gesture segmentation recognition system |
| CN103839040A (en) * | 2012-11-27 | 2014-06-04 | 株式会社理光 | Gesture identification method and device based on depth images |
| WO2014113507A1 (en) * | 2013-01-15 | 2014-07-24 | Leap Motion, Inc. | Dynamic user interactions for display control and customized gesture interpretation |
| CN103198297A (en) * | 2013-03-15 | 2013-07-10 | 浙江大学 | Kinematic similarity assessment method based on correlation geometrical characteristics |
Cited By (57)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104394386A (en) * | 2014-12-11 | 2015-03-04 | 盐城工学院 | System and method for evaluating knee joint motion normativity through multi-view sequence images |
| CN104486590A (en) * | 2014-12-26 | 2015-04-01 | 安徽寰智信息科技股份有限公司 | Video acquisition and processing method for golf teaching and training |
| CN105196298A (en) * | 2015-10-16 | 2015-12-30 | 费文杰 | Non-contact interaction doll display system and non-contact interaction doll display method |
| CN105196298B (en) * | 2015-10-16 | 2017-02-01 | 费文杰 | Non-contact interaction doll display system and non-contact interaction doll display method |
| CN105307017A (en) * | 2015-11-03 | 2016-02-03 | Tcl集团股份有限公司 | Method and device for correcting posture of smart television user |
| CN105534528A (en) * | 2015-12-08 | 2016-05-04 | 杭州电子科技大学 | Non-contact physical test system and test method based on somatosensory recognition |
| CN105534528B (en) * | 2015-12-08 | 2018-03-23 | 杭州电子科技大学 | A kind of contactless physical fitness test system and method for testing based on somatosensory recognition |
| CN105664462A (en) * | 2016-01-07 | 2016-06-15 | 北京邮电大学 | Auxiliary training system based on human body posture estimation algorithm |
| CN106974656A (en) * | 2016-01-15 | 2017-07-25 | 赵敏岗 | For gathering motion state and carrying out the system and implementation method of real time contrast's correction |
| CN105816182A (en) * | 2016-03-24 | 2016-08-03 | 西安交通大学 | Method for measuring cervical vertebra motion degree on basis of Kinect sensor |
| CN105999670A (en) * | 2016-05-31 | 2016-10-12 | 山东科技大学 | Shadow-boxing movement judging and guiding system based on kinect and guiding method adopted by same |
| CN107469294A (en) * | 2016-06-08 | 2017-12-15 | 上海体育学院 | A kind of paddler's motion analysis system based on KINECT hardware |
| CN106372294A (en) * | 2016-08-30 | 2017-02-01 | 苏州品诺维新医疗科技有限公司 | Method and device for correcting posture |
| CN108090394A (en) * | 2016-11-21 | 2018-05-29 | 风跑体育发展（深圳）有限公司 | A kind of running action automatic tracking method and its system |
| CN106650687A (en) * | 2016-12-30 | 2017-05-10 | 山东大学 | Posture correction method based on depth information and skeleton information |
| CN106923567A (en) * | 2017-04-01 | 2017-07-07 | 浙江陀曼精密机械有限公司 | A kind of intelligent health chair appearance method of data capture |
| CN107050774B (en) * | 2017-05-17 | 2019-04-16 | 上海电机学院 | A kind of body-building movement error correction system and method based on movement acquisition |
| CN107050774A (en) * | 2017-05-17 | 2017-08-18 | 上海电机学院 | A kind of body-building action error correction system and method based on action collection |
| CN107767930A (en) * | 2017-10-13 | 2018-03-06 | 广东工业大学 | A kind of smart motion bearing calibration, device and equipment |
| WO2019075824A1 (en) * | 2017-10-20 | 2019-04-25 | 深圳市鹰硕技术有限公司 | System for correcting and training running posture of child |
| CN108211312A (en) * | 2017-11-30 | 2018-06-29 | 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 |
| CN108256433A (en) * | 2017-12-22 | 2018-07-06 | 银河水滴科技（北京）有限公司 | A kind of athletic posture appraisal procedure and system |
| CN108542021A (en) * | 2018-03-18 | 2018-09-18 | 江苏特力威信息系统有限公司 | A kind of gym suit and limbs measurement method and device based on vitta identification |
| CN110353691A (en) * | 2018-04-10 | 2019-10-22 | 仁宝电脑工业股份有限公司 | Act assessment system, its method and non-transient computer-readable recording medium |
| CN108537284A (en) * | 2018-04-13 | 2018-09-14 | 东莞松山湖国际机器人研究院有限公司 | Posture assessment scoring method based on computer vision deep learning algorithm and system |
| CN108905164A (en) * | 2018-05-29 | 2018-11-30 | 广东工业大学 | A kind of donning system for correcting athletic posture |
| CN109274883A (en) * | 2018-07-24 | 2019-01-25 | 广州虎牙信息科技有限公司 | Posture antidote, device, terminal and storage medium |
| CN109274883B (en) * | 2018-07-24 | 2022-02-01 | 广州虎牙信息科技有限公司 | Posture correction method, device, terminal and storage medium |
| CN112911393A (en) * | 2018-07-24 | 2021-06-04 | 广州虎牙信息科技有限公司 | Part recognition method, device, terminal and storage medium |
| CN109222909A (en) * | 2018-09-30 | 2019-01-18 | 李莉 | A kind of wearable intelligent monitoring device and the method for monitoring movement, spinal curvature and joint wear |
| CN111460868A (en) * | 2019-01-22 | 2020-07-28 | 上海形趣信息科技有限公司 | Action recognition error correction method, system, electronic device and storage medium |
| CN110338806A (en) * | 2019-07-09 | 2019-10-18 | 四川大学华西第二医院 | The correct posture correction system of pregnant woman |
| CN110338807A (en) * | 2019-07-09 | 2019-10-18 | 四川大学华西第二医院 | Pregnant woman's attitude updating and monitoring system |
| CN110866440A (en) * | 2019-09-27 | 2020-03-06 | 惠州市德赛西威汽车电子股份有限公司 | Pointer instrument deep learning network building method, detection method and system |
| CN110866440B (en) * | 2019-09-27 | 2024-06-07 | 惠州市德赛西威汽车电子股份有限公司 | Pointer instrument deep learning network construction method, pointer instrument deep learning network detection method and pointer instrument deep learning network construction system |
| CN110782482A (en) * | 2019-10-21 | 2020-02-11 | 深圳市网心科技有限公司 | Motion evaluation method and device, computer equipment and storage medium |
| CN110751100A (en) * | 2019-10-22 | 2020-02-04 | 北京理工大学 | Auxiliary training method and system for stadium |
| CN110796077A (en) * | 2019-10-29 | 2020-02-14 | 湖北民族大学 | Attitude motion real-time detection and correction method |
| CN111067597B (en) * | 2019-12-10 | 2021-04-16 | 山东大学 | System for determining puncture path according to human body posture in tumor puncture |
| CN111067597A (en) * | 2019-12-10 | 2020-04-28 | 山东大学 | System and method for determining puncture path according to human body posture in tumor puncture |
| CN113297876A (en) * | 2020-02-21 | 2021-08-24 | 佛山市云米电器科技有限公司 | Motion posture correction method based on intelligent refrigerator, intelligent refrigerator and storage medium |
| WO2021169223A1 (en) * | 2020-02-24 | 2021-09-02 | 五邑大学 | Learning-type robot, and learning correction method based on same |
| CN111359159A (en) * | 2020-03-24 | 2020-07-03 | 成都翡铭科技有限公司 | Cervical vertebra rehabilitation training method |
| CN111803905A (en) * | 2020-06-04 | 2020-10-23 | 上海市东方医院（同济大学附属东方医院） | Parkinson's disease patient muscle activity monitor |
| CN111985443A (en) * | 2020-09-01 | 2020-11-24 | 安徽炬视科技有限公司 | Robust human body posture estimation algorithm |
| CN112487965B (en) * | 2020-11-30 | 2023-01-31 | 重庆邮电大学 | Intelligent fitness action guiding method based on 3D reconstruction |
| CN112487965A (en) * | 2020-11-30 | 2021-03-12 | 重庆邮电大学 | Intelligent fitness action guiding method based on 3D reconstruction |
| CN112422946B (en) * | 2020-11-30 | 2023-01-31 | 重庆邮电大学 | Intelligent yoga action guidance system based on 3D reconstruction |
| CN112422946A (en) * | 2020-11-30 | 2021-02-26 | 重庆邮电大学 | Intelligent yoga action guidance system based on 3D reconstruction |
| CN112714328A (en) * | 2020-12-23 | 2021-04-27 | 作业帮教育科技（北京）有限公司 | Live course student posture prompting method and device and electronic equipment |
| CN112668531A (en) * | 2021-01-05 | 2021-04-16 | 重庆大学 | Motion posture correction method based on motion recognition |
| CN112883808A (en) * | 2021-01-23 | 2021-06-01 | 招商新智科技有限公司 | Method and device for detecting abnormal behavior of pedestrian riding escalator and electronic equipment |
| CN113367688A (en) * | 2021-04-28 | 2021-09-10 | 北京理工大学 | Hemiplegia rating method and system based on human body static gait and TOF camera |
| TWI822473B (en) * | 2022-11-18 | 2023-11-11 | 財團法人資訊工業策進會 | Method, processing control device and system of providing movement improvement information |
| CN117078885A (en) * | 2023-09-07 | 2023-11-17 | 广州市创佳建筑模型有限公司 | Building model spliced sand table coordinate and posture guiding system based on feature recognition |
| CN117558457A (en) * | 2024-01-11 | 2024-02-13 | 合肥特斯塔信息科技有限公司 | Customer portrait analysis method in customer relationship management system |
| CN117558457B (en) * | 2024-01-11 | 2024-03-26 | 合肥特斯塔信息科技有限公司 | Customer portrait analysis method in customer relationship management system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104200491A (en) | Motion posture correcting system for human body | |
| US11132533B2 (en) | Systems and methods for creating target motion, capturing motion, analyzing motion, and improving motion | |
| CN107050774B (en) | A kind of body-building movement error correction system and method based on movement acquisition | |
| CN110650354B (en) | Live broadcast method, system, equipment and storage medium for virtual cartoon character | |
| CN108107592B (en) | The calibration of virtual reality system | |
| CN109214231A (en) | Physical education auxiliary system and method based on human body attitude identification | |
| US8282481B2 (en) | System and method for cyber training of martial art on network | |
| US11872468B2 (en) | Sport training method and system and head-mounted VR device | |
| CN103390174A (en) | Physical education assisting system and method based on human body posture recognition | |
| US9418470B2 (en) | Method and system for selecting the viewing configuration of a rendered figure | |
| CN106843507B (en) | Virtual reality multi-person interaction method and system | |
| KR102251315B1 (en) | Exercise training system | |
| CN110544302A (en) | Human body action reconstruction system and method based on multi-view vision and action training system | |
| CN110221691B (en) | Immersive virtual experience method, system and device | |
| CN104090664B (en) | A kind of interactive projection method, apparatus and system | |
| KR102594938B1 (en) | Apparatus and method for comparing and correcting sports posture using neural network | |
| KR101555863B1 (en) | Device and method for taekwondo poomsae readout and education | |
| JP2005198818A (en) | Learning supporting system for bodily motion and learning supporting method | |
| KR20230086874A (en) | Rehabilitation training system using 3D body precision tracking technology | |
| CN112288876A (en) | Long-distance AR identification server and system | |
| CN106708266A (en) | AR action correction projection method and system based on binocular gesture recognition | |
| Zhou | Role of human body posture recognition method based on wireless network Kinect in line dance aerobics and gymnastics training | |
| KR101240418B1 (en) | Robot teaching system using real-time and non-contact type motion imitation system and method thereof | |
| KR101094137B1 (en) | Motion capture system | |
| KR102299381B1 (en) | Augmented reality training system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20141210 |
|
| WD01 | Invention patent application deemed withdrawn after publication |