CN108830206A - A kind of course axis Internet Educational System - Google Patents
A kind of course axis Internet Educational System Download PDFInfo
- Publication number
- CN108830206A CN108830206A CN201810574044.3A CN201810574044A CN108830206A CN 108830206 A CN108830206 A CN 108830206A CN 201810574044 A CN201810574044 A CN 201810574044A CN 108830206 A CN108830206 A CN 108830206A
- Authority
- CN
- China
- Prior art keywords
- course
- behavior
- internet
- bone
- axis
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Social Psychology (AREA)
- Economics (AREA)
- Human Computer Interaction (AREA)
- Psychiatry (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a kind of course axis Internet Educational Systems, what is solved is that course selects complicated technical problem, by using the course axis Internet Educational System for infant behavior training, including behavior acquisition system, with the internet analysis center of behavior acquisition system network connection, internet analysis center is connected with user terminal；Internet analysis center includes processor and memory, and behavior database and course library are stored in memory, and behavioral data is corresponding with lesson data；Behavior the matching analysis program is also stored in memory, course axis generates program；Course axis generates the technical solution that program is executed by processor, preferably resolves the problem, can be used in Internet education.
Description
Technical field
The present invention relates to Internet education fields, and in particular to a kind of course axis Internet Educational System.
Background technique
Children education is completed by kindergarten and other early childhood institutions for specially opening up, it can influence child's body at
Long and cognition, emotion, personality etc. development, are the important rings in education system.Action behavior education is based on child
The educational mode that situation is taught through lively activities.And after internet is added, it can be remembered by the detection and judgement for behavior outcome
It records the mistake of conduct education and as a result, to promote the progress of conduct education course axis.
But existing course axis Internet Educational System selects complicated technical problem there are course.Therefore it provides one
The course axis Internet Educational System of kind automatical curricula-variable journey composition course axis is with regard to necessary.
Summary of the invention
Complicated technical problem is selected the technical problem to be solved by the present invention is to course existing in the prior art.It provides
A kind of new course axis Internet Educational System, the course axis Internet Educational System are selected simple, course axis with course and are chosen
Select accurate feature.
In order to solve the above technical problems, the technical solutions adopted are as follows：
A kind of course axis Internet Educational System, the course axis Internet Educational System is for infant behavior training, packet
Behavior acquisition system is included, the internet analysis center with the network connection of behavior acquisition system, internet analysis center connects useful
Family terminal；Internet analysis center includes processor and memory, and behavior database and course library, behavior are stored in memory
Data are corresponding with lesson data；Behavior the matching analysis program is also stored in memory, course axis generates program；Course axis generates
Program is executed by processor, is included the following steps：
Step 1, the action video that the course in mark course library includes is recorded, action video is subjected to image zooming-out, is taken
The course bone sequence and feature that image bone Activity recognition method Give lecture includes；
Step 2, course name is defined, course bone sequence and feature under corresponding course name are encapsulated；
Step 3, the result of definition matching behavioural analysis program is as behavioural analysis as a result, bonding behavior is analyzed result, divided
Course needed for analysis object identity data determine course axis；
Step 4, the course according to needed for course axis calls course bone sequence and feature composition class under corresponding course name
Journey axis programmed check library.
The working principle of the invention：The present invention constructs the acquisition system of a students ' behavior action data, generally uses
Camera carries out Image Acquisition, and passes through behavior matching and course as analysis system by the server system of network connection
Axis generates and selects Behavioral training course composition course axis automatically, convenient and efficient, has liberated teacher or parent selects the worry of course.
Existing psychological study and child's research are capable of providing how should receive according to child current behavior state analysis child
Which kind of state.Analysis and summary is a set of which kind of movement which kind of aspect of infant can be trained using for external early childhood education
Corresponding relationship.And the present invention completes course and selects mainly by accurate, simple action recognition, while with action recognition with
Aspect ratio pair in course library examines the course performance of infant.
In above scheme, for optimization, further, the behavior the matching analysis program includes：
Behavior video data is carried out image zooming-out, taken by step A, the behavior video data of reception behavior features acquisition system
Image bone Activity recognition method identifies behavior sequence and skeleton character；
Step B will be matched in behavior sequence and skeleton character sequence and course axis programmed check library, and successful match is then
It defines the course frequency of training and adds one, it fails to match then defines this time study in vain.
Further, described image bone Activity recognition method includes：
Step 1.1, human body behavior act is defined as rigid body displacement, and decomposing rigid body displacement is rigid body translation and rigidity
Homogeneous matrix Lie group SX (3) is represented rigid body displacement by body rotation, and wherein homogeneous matrix Lie group SX (3) is by Lie algebra ST (3) table
Sign；
Step 1.2, the skeleton model C (t) that method is described based on Lie algebra ST (3) relative characteristic is established, to skeleton model C
(t) difference processing is carried out；Defining in skeleton model C (t) has N sections of bone rigid bodies, and first segment bone is defined as the when time t
The displacement result of two sections of bones defines the displacement mapping relations between first segment bone and second segment bone；Use theorem in Euclid space
The displacement mapping relations are expressed as homogeneous matrix Lie group SX (3), it then will Lee's generation corresponding with homogeneous matrix Lie group SX (3)
Number ST (3) is used as motion feature, and wherein N is positive integer；
Step 1.3, it using skeleton model C (t) described in the regular method alignment step 1.2 of depth typical time period, is aligned
Feature samples；
Step 1.4, using alignment feature sample in correlative character amendment step 1.3, amendment alignment feature sample is obtained；
Correlative character amendment includes being aligned skeleton model C (t) with alignment feature sample, calculate skeleton model C (t) and
The correlation of each frame in alignment feature sample calculates correction factor for related coefficient x ∈ R as variable, correction factor is multiplied
Using the characteristic of each frame as the weight of corresponding frame, the correction factor obeys correction function ex；
Step 1.5, classified using support vector machines to amendment alignment feature sample, obtain course bone sequence and spy
Sign.
Further, the regular method of depth typical time period described in step 1.3 is regular including integrating depth typical time period
Method.
Further, the processing of difference described in step 1.2 includes that the identical feature of frame number, interpolation are obtained using interpolation method
The interpolation formula of method is QN∈ SX (3) is tnThe instantaneous relative position at moment：
Wherein,
Further, the course includes life activities course, and life activities course includes big-movement, is acted in environment,
Refine action control.
Further, movement includes walking in the environment, walks in empty environment, the environment of household is disposed at one
Middle walking stands and sits down, sits down or stand on chair；It removes, removes standard blanket, remove chair, move disk empty, remove kettle, remove desk；
End, carries a tray, and holds cup, and end is equipped with the plate of tableware.
Beneficial effects of the present invention：The present invention selects course by detection infant movement automatically and forms course axis for teaching
It learns, it is simple and convenient；And pass through the course performance for detecting course axis automatically, the education of real-time iterative method infant.Separately
Outside, execution identification is identified by efficient accurate bone, it is ensured that because of Activity recognition error caused by the error of clothing.It is logical
Cross that depth typical time period is regular and Relative modification alignment improves recognition accuracy using fusion；Overcome existing Activity recognition
Defect；Use the fusion depth typical time period regular calculating time for significantly reducing Activity recognition.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples.
Fig. 1, course axis generate program schematic diagram.
Fig. 2, behavior the matching analysis program schematic diagram.
Fig. 3, image bone Activity recognition method schematic diagram.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to embodiments, to the present invention
It is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, is not used to limit
The fixed present invention.
Embodiment 1
The present embodiment provides a kind of course axis Internet Educational System, the course axis Internet Educational System is used for child
Behavioral training, including behavior acquisition system, with behavior acquisition system network connection internet analysis center, internet analysis in
The heart is connected with user terminal；Internet analysis center includes processor and memory, be stored in memory behavior database and
Course library, behavioral data are corresponding with lesson data；Behavior the matching analysis program is also stored in memory, course axis generates journey
Sequence；Such as Fig. 1, course axis generates program and is executed by processor, included the following steps：
Step 1, the action video that the course in mark course library includes is recorded, action video is subjected to image zooming-out, is taken
The course bone sequence and feature that image bone Activity recognition method Give lecture includes；
Step 2, course name is defined, course bone sequence and feature under corresponding course name are encapsulated；
Step 3, the result of definition matching behavioural analysis program is as behavioural analysis as a result, bonding behavior is analyzed result, divided
Course needed for analysis object identity data determine course axis；
Step 4, the course according to needed for course axis calls course bone sequence and feature composition class under corresponding course name
Journey axis programmed check library.
The behavior acquisition system of the present embodiment uses the Florence3D-Action data set conduct made by Kinect
Experimental subjects.It includes 3 cameras that Kinect, which has altogether, and intermediate is RGB camera, is 640 × 480 for capturing resolution ratio
Color image, each second obtain 30 frame images, and both sides are two depth transducers, for detecting the relative position of infant.
Florence3D-Action data set collects data using the fixed Kinect sensor in a position.People is assumed in this implementation
Some higher joints of correlation are relatively fixed constant in body, and the trunk of human body is a biggish rigid body.On skeleton
Joint has been divided into two-stage：Level-one is the artis on trunk；Second level is to be located at outside trunk to pass through bone phase with level-one joint
Sub- artis even.In order to determine the position in level-one joint, model establishes coordinate system as origin using the vertebra tail position of human body,
Obtain coordinate (u, r, t)O, (u, r, t)1, (u, r, t)2(u, r, t)3.Using each level-one as coordinate origin, establishes sit respectively
Mark system obtains second level body joint point coordinate.
Specifically, such as Fig. 2, the behavior the matching analysis program includes：
Behavior video data is carried out image zooming-out, taken by step A, the behavior video data of reception behavior features acquisition system
Image bone Activity recognition method identifies behavior sequence and skeleton character；
Step B will be matched in behavior sequence and skeleton character sequence and course axis programmed check library, and successful match is then
It defines the course frequency of training and adds one, it fails to match then defines this time study in vain.
Specifically, such as Fig. 3, described image bone Activity recognition method includes：
Step 1.1, human body behavior act is defined as rigid body displacement, and decomposing rigid body displacement is rigid body translation and rigidity
Homogeneous matrix Lie group SX (3) is represented rigid body displacement by body rotation, and wherein homogeneous matrix Lie group SX (3) is by Lie algebra ST (3) table
Sign；
Step 1.2, the skeleton model C (t) that method is described based on Lie algebra ST (3) relative characteristic is established, to skeleton model C
(t) difference processing is carried out；Defining in skeleton model C (t) has N sections of bone rigid bodies, and first segment bone is defined as the when time t
The displacement result of two sections of bones defines the displacement mapping relations between first segment bone and second segment bone；Use theorem in Euclid space
The displacement mapping relations are expressed as homogeneous matrix Lie group SX (3), it then will Lee's generation corresponding with homogeneous matrix Lie group SX (3)
Number ST (3) is used as motion feature, and wherein N is positive integer；
Step 1.3, it using skeleton model C (t) described in the regular method alignment step 1.2 of depth typical time period, is aligned
Feature samples；The regular method of depth typical time period of the present embodiment uses the existing regular method of depth typical time period；Preferably,
The time is calculated to reduce.The regular preferably fusion regular method of depth typical time period of depth typical time period is aligned；
Step 1.4, using alignment feature sample in correlative character amendment step 1.3, amendment alignment feature sample is obtained；
Correlative character amendment includes being aligned skeleton model C (t) with alignment feature sample, calculate skeleton model C (t) and
The correlation of each frame in alignment feature sample calculates correction factor for related coefficient x ∈ R as variable, correction factor is multiplied
Using the characteristic of each frame as the weight of corresponding frame, the correction factor obeys correction function ex；By repairing for correlation
After just, the Activity recognition method movement raising lower to some discriminations in the present embodiment is more obvious, such as carries a tray
With walk the two movements, the accuracy rate of identification all improves 1%-2% or so；
Step 1.5, classified using support vector machines to amendment alignment feature sample, obtain course bone sequence and spy
Sign.
Further, the regular method of depth typical time period described in step 1.3 is regular including integrating depth typical time period
Method.
Further, the processing of difference described in step 1.2 includes that the identical feature of frame number, interpolation are obtained using interpolation method
The interpolation formula of method is QN∈ SX (3) is tnThe instantaneous relative position at moment：
Wherein,
Further, the course includes life activities course, and life activities course includes big-movement, is acted in environment,
Refine action control.
Further, movement includes walking in the environment, walks in empty environment, the environment of household is disposed at one
Middle walking stands and sits down, sits down or stand on chair；It removes, removes standard blanket, remove chair, move disk empty, remove kettle, remove desk；
End, carries a tray, and holds cup, and end is equipped with the plate of tableware.
Although the illustrative specific embodiment of the present invention is described above, in order to the technology of the art
Personnel are it will be appreciated that the present invention, but the present invention is not limited only to the range of specific embodiment, to the common skill of the art
For art personnel, as long as long as various change the attached claims limit and determine spirit and scope of the invention in, one
The innovation and creation using present inventive concept are cut in the column of protection.
Claims (7)
1. a kind of course axis Internet Educational System, it is characterised in that：The course axis Internet Educational System is used for child's row
For training, including behavior acquisition system, the internet analysis center being connected to the network with behavior acquisition system, internet analysis center
It is connected with user terminal；
Internet analysis center includes processor and memory, and behavior database and course library, behavior number are stored in memory
According to corresponding with lesson data；Behavior the matching analysis program is also stored in memory, course axis generates program；
Course axis generates program and is executed by processor, includes the following steps：
Step 1, the action video that the course in mark course library includes is recorded, action video is subjected to image zooming-out, takes image
The course bone sequence and feature that bone Activity recognition method Give lecture includes；
Step 2, course name is defined, course bone sequence and feature under corresponding course name are encapsulated；
Step 3, the result of definition matching behavioural analysis program is as behavioural analysis as a result, bonding behavior analysis result, analysis pair
Course needed for determining course axis as identity data；
Step 4, the course according to needed for course axis calls course bone sequence and feature under corresponding course name to form course axis
Programmed check library.
2. course axis Internet Educational System according to claim 1, it is characterised in that：The behavior the matching analysis program
Including：
Behavior video data is carried out image zooming-out, takes image by step A, the behavior video data of reception behavior features acquisition system
Bone Activity recognition method identifies behavior sequence and skeleton character；
Step B will be matched in behavior sequence and skeleton character sequence and course axis programmed check library, and successful match then defines
The course frequency of training adds one, and it fails to match then defines this time study in vain.
3. course axis Internet Educational System according to claim 1 or 2, it is characterised in that：Described image bone behavior
Recognition methods includes：
Step 1.1, human body behavior act is defined as rigid body displacement, and decomposing rigid body displacement is rigid body translation and rigid body rotation
Turn, homogeneous matrix Lie group SX (3) is represented into rigid body displacement, wherein homogeneous matrix Lie group SX (3) is characterized by Lie algebra ST (3)；
Step 1.2, the skeleton model C (t) that method is described based on Lie algebra ST (3) relative characteristic is established, to skeleton model C (t)
Carry out difference processing；Defining in skeleton model C (t) has N sections of bone rigid bodies, and first segment bone is defined as second when time t
The displacement result of section bone, defines the displacement mapping relations between first segment bone and second segment bone；It will using theorem in Euclid space
The displacement mapping relations are expressed as homogeneous matrix Lie group SX (3), then will Lie algebra corresponding with homogeneous matrix Lie group SX (3)
ST (3) is used as motion feature, and wherein N is positive integer；
Step 1.3, using skeleton model C (t) described in the regular method alignment step 1.2 of depth typical time period, alignment feature is obtained
Sample；
Step 1.4, using alignment feature sample in correlative character amendment step 1.3, amendment alignment feature sample is obtained；It is described
Correlative character amendment include being aligned skeleton model C (t) with alignment feature sample, calculating skeleton model C (t) be aligned
The correlation of each frame in feature samples calculates correction factor for related coefficient x ∈ R as variable, by correction factor multiplied by every
Weight of the characteristic of one frame as corresponding frame, the correction factor obey correction function ex；
Step 1.5, classified using support vector machines to amendment alignment feature sample, obtain course bone sequence and feature.
4. course axis Internet Educational System according to claim 3, it is characterised in that：Depth described in step 1.3
The regular method of typical time period includes integrating the regular method of depth typical time period.
5. course axis Internet Educational System according to claim 3, it is characterised in that：At difference described in step 1.2
Reason includes that the identical feature of frame number is obtained using interpolation method, and the interpolation formula of interpolation method is QN∈ SX (3) is tnMoment
Instantaneous relative position：
Wherein,
6. -5 any course axis Internet Educational System according to claim 1, it is characterised in that：The course includes life
Course is made in activity, and life activities course includes big-movement, and movement in environment refines action control.
7. course axis Internet Educational System according to claim 1, it is characterised in that：It is acted in the environment and includes
It walks, walks in empty environment, walk in an environment for being disposed with household, stand and sit down, sit down or stand on chair
It rises；It removes, removes standard blanket, remove chair, move disk empty, remove kettle, remove desk；End, carries a tray, and holds cup, and end is equipped with the plate of tableware.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810574044.3A CN108830206A (en) | 2018-06-06 | 2018-06-06 | A kind of course axis Internet Educational System |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810574044.3A CN108830206A (en) | 2018-06-06 | 2018-06-06 | A kind of course axis Internet Educational System |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108830206A true CN108830206A (en) | 2018-11-16 |
Family
ID=64144453
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810574044.3A Pending CN108830206A (en) | 2018-06-06 | 2018-06-06 | A kind of course axis Internet Educational System |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108830206A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110414306A (en) * | 2019-04-26 | 2019-11-05 | 吉林大学 | A kind of Infants With Abnormal behavioral value method based on meanshift algorithm and SVM |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102397680A (en) * | 2011-12-06 | 2012-04-04 | 北京市莱科智多教育科技有限公司 | System and method for training fine movement |
| CN103258450A (en) * | 2013-03-22 | 2013-08-21 | 华中师范大学 | Intelligent learning platform for children with autism |
| CN104524742A (en) * | 2015-01-05 | 2015-04-22 | 河海大学常州校区 | Cerebral palsy child rehabilitation training method based on Kinect sensor |
| CN106060653A (en) * | 2016-06-08 | 2016-10-26 | 武汉鸿瑞达信息技术有限公司 | Method for filtering improper action in live internet video |
| CN106448295A (en) * | 2016-10-20 | 2017-02-22 | 泉州市开拓者智能科技有限公司 | Remote teaching system and method based on capturing |
| CN106880357A (en) * | 2017-01-05 | 2017-06-23 | 首都体育学院 | A kind of locomitivity assessment system |
| CN106910382A (en) * | 2017-05-03 | 2017-06-30 | 深圳市儒侠教育科技有限公司 | The autonomous on-line study method of course based on VR videos |
| CN107229920A (en) * | 2017-06-08 | 2017-10-03 | 重庆大学 | Based on integrating, depth typical time period is regular and Activity recognition method of related amendment |
| CN107551521A (en) * | 2017-08-17 | 2018-01-09 | 广州视源电子科技股份有限公司 | Exercise guide method and device, smart machine and storage medium |
| CN107644556A (en) * | 2017-10-11 | 2018-01-30 | 四川省电科互联网加产业技术研究院有限公司 | Internet education method and system based on school |
-
2018
- 2018-06-06 CN CN201810574044.3A patent/CN108830206A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102397680A (en) * | 2011-12-06 | 2012-04-04 | 北京市莱科智多教育科技有限公司 | System and method for training fine movement |
| CN103258450A (en) * | 2013-03-22 | 2013-08-21 | 华中师范大学 | Intelligent learning platform for children with autism |
| CN104524742A (en) * | 2015-01-05 | 2015-04-22 | 河海大学常州校区 | Cerebral palsy child rehabilitation training method based on Kinect sensor |
| CN106060653A (en) * | 2016-06-08 | 2016-10-26 | 武汉鸿瑞达信息技术有限公司 | Method for filtering improper action in live internet video |
| CN106448295A (en) * | 2016-10-20 | 2017-02-22 | 泉州市开拓者智能科技有限公司 | Remote teaching system and method based on capturing |
| CN106880357A (en) * | 2017-01-05 | 2017-06-23 | 首都体育学院 | A kind of locomitivity assessment system |
| CN106910382A (en) * | 2017-05-03 | 2017-06-30 | 深圳市儒侠教育科技有限公司 | The autonomous on-line study method of course based on VR videos |
| CN107229920A (en) * | 2017-06-08 | 2017-10-03 | 重庆大学 | Based on integrating, depth typical time period is regular and Activity recognition method of related amendment |
| CN107551521A (en) * | 2017-08-17 | 2018-01-09 | 广州视源电子科技股份有限公司 | Exercise guide method and device, smart machine and storage medium |
| CN107644556A (en) * | 2017-10-11 | 2018-01-30 | 四川省电科互联网加产业技术研究院有限公司 | Internet education method and system based on school |
Non-Patent Citations (1)
| Title |
|---|
| 刘建平等: "基于互联网的体育远程教育系统设计", 《武汉体育学院学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110414306A (en) * | 2019-04-26 | 2019-11-05 | 吉林大学 | A kind of Infants With Abnormal behavioral value method based on meanshift algorithm and SVM |
| CN110414306B (en) * | 2019-04-26 | 2022-07-19 | 吉林大学 | Baby abnormal behavior detection method based on meanshift algorithm and SVM |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Thar et al. | A proposal of yoga pose assessment method using pose detection for self-learning | |
| CN111368810B (en) | Sit-up detection system and method based on human body and skeleton key point identification | |
| CN107754225A (en) | A kind of intelligent body-building coaching system | |
| CN112861624A (en) | Human body posture detection method, system, storage medium, equipment and terminal | |
| Díaz et al. | DTCoach: your digital twin coach on the edge during COVID-19 and beyond | |
| US11872468B2 (en) | Sport training method and system and head-mounted VR device | |
| CN1960674A (en) | System and method for ergonomic tracking for individual physical exertion | |
| Pagnon et al. | Pose2Sim: An end-to-end workflow for 3D markerless sports kinematics—Part 1: Robustness | |
| US11826140B2 (en) | System and method for human motion detection and tracking | |
| CN113762133A (en) | Self-weight fitness auxiliary coaching system, method and terminal based on human body posture recognition | |
| Zou et al. | Intelligent fitness trainer system based on human pose estimation | |
| CN110717391A (en) | Height measuring method, system, device and medium based on video image | |
| CN108830206A (en) | A kind of course axis Internet Educational System | |
| CN110559639A (en) | Robot teaching method for gymnastics movement | |
| Xiong et al. | Robust vision-based workout analysis using diversified deep latent variable model | |
| Ray et al. | Pressim: An end-to-end framework for dynamic ground pressure profile generation from monocular videos using physics-based 3d simulation | |
| Kinger et al. | Deep learning based yoga pose classification | |
| Hirasawa et al. | Promotion system for home-based squat training using openpose | |
| Masullo et al. | CaloriNet: From silhouettes to calorie estimation in private environments | |
| Guanoluisa et al. | GY MEDIC: analysis and rehabilitation system for patients with facial paralysis | |
| CN115006822A (en) | Intelligent fitness mirror control system | |
| CN111507920B (en) | Bone motion data enhancement method and system based on Kinect | |
| Chaudhary et al. | Real-Time Yoga Pose Detection Using OpenCV and MediaPipe | |
| WO2022196059A1 (en) | Information processing device, information processing method, and program | |
| CN116153510B (en) | Correction mirror control method, device, equipment, storage medium and intelligent correction mirror |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181116 |
|
| RJ01 | Rejection of invention patent application after publication |