CN110782967A - Fitness action standard degree evaluation method and device - Google Patents
Fitness action standard degree evaluation method and device Download PDFInfo
- Publication number
- CN110782967A CN110782967A CN201911058207.3A CN201911058207A CN110782967A CN 110782967 A CN110782967 A CN 110782967A CN 201911058207 A CN201911058207 A CN 201911058207A CN 110782967 A CN110782967 A CN 110782967A
- Authority
- CN
- China
- Prior art keywords
- time
- action
- recognition
- standard
- fitness
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/30—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses a method and a device for evaluating fitness action standard degree, which set an action identification time interval for each fitness action in a fitness template video, the exercise recognition time interval of each exercise action is readjusted, the recognition starting time of an action recognition time interval after the recognition ending time of a previous action recognition time interval in two adjacent action recognition time intervals lags is avoided, time scoring value calculation is carried out on the exercise actions according to the action recognition time interval of each exercise action and the action ending time of the exercise actions, the time scoring value can be independently used as a standard degree scoring value to evaluate whether the exercise actions are standard or not, and can also be combined with the force scoring value obtained through action recognition to evaluate whether the exercise actions are standard or not, and therefore the exercise finishing time can be accurately evaluated.
Description
Technical Field
The invention relates to the technical field of sports application, in particular to a fitness action standard degree evaluation method and device.
Background
With the increasing living standard of people, people pay more and more attention to physical exercise. Meanwhile, people live with various kinds of fitness software to help people to exercise. The existing fitness software is used for helping a user build fitness by playing a fitness template video and learning and simulating the video while watching the video. However, the existing body-building software cannot monitor whether the body-building action of the user is standard or not, and cannot realize body sensing detection. Although some motion sensing detection applications, such as motion sensing games, can detect the motion of a user at present, the motion sensing detection applications can only detect that the user does not make a certain simple motion (for example, waving his hand), cannot detect the time taken by the user for a fitness motion, are difficult to detect complex motions such as fitness, and cannot guide the user to achieve a good training effect.
Disclosure of Invention
The invention mainly solves the technical problem of providing a fitness action standard degree evaluation method which can accurately evaluate the completion time of fitness action.
In order to solve the technical problems, the invention adopts a technical scheme that: the method for evaluating the fitness action standard degree comprises the following steps of; acquiring standard starting time and standard ending time of each body building action in a body building template video, setting an action identification time interval of each body building action, extending the standard starting time of each body building action forwards for a first preset time as identification starting time of the action identification time interval, and extending the standard ending time of each body building action backwards for a second preset time as identification ending time of the action identification time interval; judging whether the recognition ending time of the previous action recognition time interval in the two adjacent action recognition time intervals lags behind the recognition starting time of the next action recognition time interval; if the judgment result is lag, sequentially adding the recognition end time and the standard end time of the previous action recognition time interval, the recognition start time and the standard start time of the next action recognition time interval into the regulating array in ascending order; taking the average value of the sum of the second element and the third element of the regulating array as reference time, replacing the recognition ending time of the previous action recognition time interval with the difference between the reference time and the preset delay time, and replacing the recognition starting time of the next action recognition time interval with the sum of the reference time and the preset delay time; acquiring fitness data of a user, performing action recognition on each fitness action according to the fitness data to obtain a recognition result, and recording the action ending time of each fitness action; judging whether the action end time of the current body-building action is greater than a standard end time; if so, taking the ratio of the difference between the recognition end time and the action end time to the difference between the recognition end time and the standard end time as the time score value of the current body-building action, and otherwise, taking the ratio of the difference between the action end time and the recognition start time to the difference between the standard end time and the recognition start time as the time score value of the current body-building action.
As a preferred embodiment of the present invention, the recognition result includes a force score value; the fitness action standard degree evaluation method further comprises the following steps: calculating the sum of the product of the time score value and the first weight value of the current body-building action and the product of the strength score value and the second weight value as a standard degree score value; wherein the sum of the first weight value and the second weight value is 1.
As a preferred embodiment of the present invention, the fitness action standard degree evaluation method further includes; comparing the standard degree score value with a plurality of pre-divided score intervals; and taking the comment corresponding to the scoring interval where the standard degree scoring value is located as an evaluation result, wherein the scoring intervals respectively correspond to different comments.
In order to solve the technical problem, the invention adopts another technical scheme that: provided is a fitness action standard degree evaluation device, including: the video analysis module is used for acquiring the standard starting time and the standard ending time of each body building action in the body building template video, setting the action recognition time interval of each body building action, extending the standard starting time of each body building action forwards by first preset time to be used as the recognition starting time of the action recognition time interval, and extending the standard ending time of each body building action backwards by second preset time to be used as the recognition ending time of the action recognition time interval; the time comparison module is used for judging whether the recognition ending time of the previous action recognition time interval in the two adjacent action recognition time intervals lags the recognition starting time of the next action recognition time interval or not, and sequentially adding the recognition ending time and the standard ending time of the previous action recognition time interval and the recognition starting time and the standard starting time of the next action recognition time interval into the regulating array according to the ascending order when the judgment result is that the recognition ending time and the standard ending time of the previous action recognition time interval and the recognition starting time and the standard starting time of the next action recognition time interval lag; the time setting module is used for taking the average value of the sum of the second element and the third element of the regulating array as reference time, replacing the recognition ending time of the previous action recognition time interval with the difference between the reference time and the preset delay time, and replacing the recognition starting time of the next action recognition time interval with the sum of the reference time and the preset delay time; the data acquisition module is used for acquiring fitness data of a user, performing action recognition on each fitness action according to the fitness data to obtain a recognition result and recording the action ending time of each fitness action; and the action evaluation module is used for judging whether the action ending time of the current body-building action is greater than the standard ending time, taking the ratio of the difference between the identification ending time and the action ending time to the difference between the identification ending time and the standard ending time as the time score value of the current body-building action when the judgment is yes, and taking the ratio of the difference between the action ending time and the identification starting time to the difference between the standard ending time and the identification starting time as the time score value of the current body-building action when the judgment is not yes.
As a preferred embodiment of the present invention, the recognition result includes a force score value; the action evaluation module is also used for calculating the sum of the product of the time score value and the first weight value of the current body-building action and the product of the strength score value and the second weight value as a standard degree score value; wherein the sum of the first weight value and the second weight value is 1.
As a preferred embodiment of the present invention, the action evaluation module is further configured to compare the standard degree score value with a plurality of pre-divided score intervals, and take the score corresponding to the score interval where the standard degree score value is located as an evaluation result, where the score intervals respectively correspond to different scores.
Different from the prior art, the invention has the beneficial effects that: the exercise motion completion time can be accurately evaluated by setting the motion recognition time interval for each exercise motion in the exercise template video, readjusting the motion recognition time interval of each exercise motion, avoiding the recognition start time of the motion recognition time interval after the recognition end time of the previous motion recognition time interval in the two adjacent motion recognition time intervals lags behind the recognition start time of the next motion recognition time interval, and calculating the time scoring value of each exercise motion according to the motion recognition time interval of each exercise motion and the motion end time of each exercise motion.
Drawings
Fig. 1 is a flowchart illustrating a method for evaluating fitness activity criteria according to an embodiment of the present invention.
Fig. 2 is a functional block diagram of a fitness action standard degree evaluation device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of a method for evaluating fitness action criteria according to an embodiment of the present invention. The fitness action standard degree evaluation method comprises the following steps;
s1: the method comprises the steps of obtaining standard starting time and standard ending time of each body building action in a body building template video, setting an action identification time interval of each body building action, extending the standard starting time of each body building action forwards by first preset time to serve as identification starting time of the action identification time interval, and extending the standard ending time of each body building action backwards by second preset time to serve as identification ending time of the action identification time interval.
The standard starting time and the standard ending time of each body-building action are obtained by intercepting the body-building template video according to frames, and the body-building template video can be the video marked with the standard starting time and the standard ending time of each body-building action. The user should complete the body-building action according to the standard starting time and the standard ending time, but considering the human body reaction time, when the user learns the body-building action while watching the video, the user is difficult to complete the body-building action immediately. Therefore, the user's reaction can be prevented from being delayed by extending the standard start time forward by the first predetermined time as the recognition start time of the motion recognition time interval and extending the standard end time backward by the second predetermined time as the recognition end time of the motion recognition time interval. The first predetermined time and the second predetermined time may be the same or different, and the specific value may be determined according to actual needs.
S2: and judging whether the recognition ending time of the previous motion recognition time interval in the two adjacent motion recognition time intervals lags behind the recognition starting time of the next motion recognition time interval.
For some body-building actions linked in time, the identification end time of the previous action identification time interval in two adjacent action identification time intervals may lag the identification start time of the next action identification time interval, for example, a left hook and a right hook in a boxing action, the punching speeds of the two body-building actions are very fast and continuous, the action identification time interval of the left hook may not be ended, and the action identification time interval of the right hook may be started.
S3: and if the judgment result is lag, sequentially adding the recognition end time and the standard end time of the previous action recognition time interval and the recognition start time and the standard start time of the next action recognition time interval into the regulating array in ascending order.
Wherein, the recognition end time and the standard end time of the previous action recognition time interval are respectively perRealZ and perStdZ, the recognition start time and the standard start time of the next action recognition time interval are respectively currRealA and curStdA, if perRealZ is more than curRealA, the perRealZ, the perStdZ, the curRealA and the curStdA are sequentially added into the regulating array according to ascending order. In one application scenario, assuming that the time units are milliseconds, perStdZ is 1000, perRealZ is 4000, currreala is 2000, and currstda is 3000, the adjustment array a is [ perStdZ, currreala, currstda, perRealZ ].
S4: and taking the average value of the sum of the second element and the third element of the regulating array as reference time, replacing the recognition ending time of the previous action recognition time interval by the difference between the reference time and the preset delay time, and replacing the recognition starting time of the next action recognition time interval by the sum of the reference time and the preset delay time.
Wherein, when the reference time is time, the time (a 1 + a 2)/2 (2000+3000)/2 (2500) is defined. If the preset delay time is n, the recognition end time perreal z-time-n of the previous motion recognition time interval is 2500-n, and the recognition start time curreal a-time + n of the next motion recognition time interval is 2500+ n. The preset delay time mainly introduces delay for the identification of two body-building actions, and avoids the situation that the identification of the latter body-building action is started immediately when the identification of the former body-building action is finished. The preset delay time n may be set according to actual needs, for example, in the foregoing application scenario, if n is 10 ms, perRealZ is 2490, and currreala is 2510.
S5: and acquiring fitness data of the user, performing action recognition on each fitness action according to the fitness data to obtain a recognition result, and recording the action ending time of each fitness action.
Wherein a user may wear wearable devices including, but not limited to, tri-axial accelerometers and gyroscopes to gather fitness data. The process of motion recognition for each fitness activity based on fitness data may be implemented according to prior art recognition algorithms.
S6: and judging whether the action ending time of the current body-building action is greater than the standard ending time.
S7: if so, taking the ratio of the difference between the recognition end time and the action end time to the difference between the recognition end time and the standard end time as the time score value of the current body-building action, and otherwise, taking the ratio of the difference between the action end time and the recognition start time to the difference between the standard end time and the recognition start time as the time score value of the current body-building action.
Wherein, the action ending time is curZ, if curZ is less than or equal to curStdZ, the time rating of the current body-building action is (curZ-curRealA)/(curStdZ-curRealA), and if curZ > curStdZ, the time rating of the current body-building action is (curRealZ-curZ)/(curRealZ-curStdZ). In one application scenario, currreala is 3000, currstda is 4000, currstdz is 7000, currrealz is 8000, if currz is 6500, the time rating of the current exercise activity is (6500-. The time score value may be used as a standard score value to evaluate whether the workout activity is standard.
Further, in a possible embodiment, the recognition result includes a force score value, and the force score value is obtained through acceleration data, gyroscope data and the like collected by the wearable device. The fitness action standard degree evaluation method further comprises the following steps:
s8: and calculating the sum of the product of the time scoring value and the first weighted value of the current body-building action and the product of the strength scoring value and the second weighted value as a standard degree scoring value.
Assuming that the standard score value is s, the standard score value is α × time score value + β × force score value, and α and β are the first weight value and the second weight value, respectively.
In order to improve the user experience and stimulate the user achievement feeling, in this embodiment, the method for evaluating the fitness action standard degree further includes:
s9: the standard degree score value is compared with a plurality of pre-divided score intervals.
S10: and taking the comment corresponding to the grading interval in which the standard degree grading value is positioned as an evaluation result, wherein the grading intervals respectively correspond to different comments.
Specifically, the plurality of scoring intervals are divided from 0 to 10, and if the scoring intervals are divided into 5 scoring intervals, they are [0,2], (2,4], (4,6], (6,8], (8, 10), and their corresponding respective scores are MISS, OK, GOOD, green, and PERFECT.
Fig. 2 is a schematic block diagram of a fitness action standard degree evaluation device according to an embodiment of the present invention. The fitness action standard degree evaluation device of the embodiment of the invention comprises a video analysis module 10, a time comparison module 20, a time setting module 30, a data acquisition module 40 and an action evaluation module 50.
The video analysis module 10 is configured to obtain a standard start time and a standard end time of each fitness action in the fitness template video, set an action recognition time interval of each fitness action, extend the standard start time of each fitness action forward by a first predetermined time as a recognition start time of the action recognition time interval, and extend the standard end time of each fitness action backward by a second predetermined time as a recognition end time of the action recognition time interval.
And the time comparison module 20 is configured to determine whether the recognition end time of the previous motion recognition time interval in the two adjacent motion recognition time intervals lags the recognition start time of the next motion recognition time interval, and when the determination result is that the recognition end time of the previous motion recognition time interval lags the recognition start time of the next motion recognition time interval, sequentially add the recognition end time and the standard end time of the previous motion recognition time interval and the recognition start time and the standard start time of the next motion recognition time interval to the adjustment array in ascending order.
And the time setting module 30 is configured to use an average value of a sum of the second element and the third element of the adjustment array as a reference time, replace the recognition ending time of the previous action recognition time interval with a difference between the reference time and a preset delay time, and replace the recognition starting time of the next action recognition time interval with a sum of the reference time and the preset delay time.
And the data acquisition module 40 is used for acquiring the fitness data of the user, performing action recognition on each fitness action according to the fitness data to obtain a recognition result and recording the action ending time of each fitness action.
And the action evaluation module 50 is used for judging whether the action ending time of the current body-building action is greater than the standard ending time, and when the judgment is yes, taking the ratio of the difference between the identification ending time and the action ending time to the difference between the identification ending time and the standard ending time as the time rating value of the current body-building action, otherwise, taking the ratio of the difference between the action ending time and the identification starting time to the difference between the standard ending time and the identification starting time as the time rating value of the current body-building action.
Further, in a possible embodiment, the recognition result includes a strength score value, and the action evaluation module 50 is further configured to calculate a sum of a product of the time score value and the first weight value of the current fitness action and a product of the strength score value and the second weight value as the standard strength score value. And the sum of the first weight value and the second weight value is 1.
In this embodiment, the action evaluation module 50 is further configured to compare the standard degree score value with a plurality of pre-divided score intervals, and take the score corresponding to the score interval where the standard degree score value is located as an evaluation result, where the score intervals respectively correspond to different scores.
The fitness action standard degree evaluation device of the embodiment of the invention has the same technical characteristics as the fitness action standard degree evaluation method of the previous embodiment, and details are not repeated herein.
Through the mode, the fitness action standard degree evaluation method and the fitness action standard degree evaluation device set the action recognition time interval for each fitness action in the fitness template video, readjust the action recognition time interval of each fitness action, avoid the situation that the recognition ending time of the previous action recognition time interval in the two adjacent action recognition time intervals lags the recognition starting time of the next action recognition time interval, and calculate the time scoring value of the fitness action according to the action recognition time interval of each fitness action and the action ending time of the fitness action, so that the finishing time of the fitness action can be accurately evaluated.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes performed by the present specification and drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (6)
1. A fitness action standard degree evaluation method is characterized by comprising the following steps;
acquiring standard starting time and standard ending time of each body building action in a body building template video, setting an action identification time interval of each body building action, extending the standard starting time of each body building action forwards for a first preset time as identification starting time of the action identification time interval, and extending the standard ending time of each body building action backwards for a second preset time as identification ending time of the action identification time interval;
judging whether the recognition ending time of the previous action recognition time interval in the two adjacent action recognition time intervals lags behind the recognition starting time of the next action recognition time interval;
if the judgment result is lag, sequentially adding the recognition end time and the standard end time of the previous action recognition time interval, the recognition start time and the standard start time of the next action recognition time interval into the regulating array in ascending order;
taking the average value of the sum of the second element and the third element of the regulating array as reference time, replacing the recognition ending time of the previous action recognition time interval with the difference between the reference time and the preset delay time, and replacing the recognition starting time of the next action recognition time interval with the sum of the reference time and the preset delay time;
acquiring fitness data of a user, performing action recognition on each fitness action according to the fitness data to obtain a recognition result, and recording the action ending time of each fitness action;
judging whether the action end time of the current body-building action is greater than a standard end time;
if so, taking the ratio of the difference between the recognition end time and the action end time to the difference between the recognition end time and the standard end time as the time score value of the current body-building action, and otherwise, taking the ratio of the difference between the action end time and the recognition start time to the difference between the standard end time and the recognition start time as the time score value of the current body-building action.
2. A fitness action criterion evaluation method according to claim 1, wherein the recognition result comprises a force score value;
the fitness action standard degree evaluation method further comprises the following steps:
calculating the sum of the product of the time score value and the first weight value of the current body-building action and the product of the strength score value and the second weight value as a standard degree score value;
wherein the sum of the first weight value and the second weight value is 1.
3. The method of evaluating fitness activity criteria according to claim 2, further comprising;
comparing the standard degree score value with a plurality of pre-divided score intervals;
and taking the comment corresponding to the scoring interval where the standard degree scoring value is located as an evaluation result, wherein the scoring intervals respectively correspond to different comments.
4. An exercise motion standard degree evaluation device, characterized in that the exercise motion standard degree evaluation device comprises:
the video analysis module is used for acquiring the standard starting time and the standard ending time of each body building action in the body building template video, setting the action recognition time interval of each body building action, extending the standard starting time of each body building action forwards by first preset time to be used as the recognition starting time of the action recognition time interval, and extending the standard ending time of each body building action backwards by second preset time to be used as the recognition ending time of the action recognition time interval;
the time comparison module is used for judging whether the recognition ending time of the previous action recognition time interval in the two adjacent action recognition time intervals lags the recognition starting time of the next action recognition time interval or not, and sequentially adding the recognition ending time and the standard ending time of the previous action recognition time interval and the recognition starting time and the standard starting time of the next action recognition time interval into the regulating array according to the ascending order when the judgment result is that the recognition ending time and the standard ending time of the previous action recognition time interval and the recognition starting time and the standard starting time of the next action recognition time interval lag;
the time setting module is used for taking the average value of the sum of the second element and the third element of the regulating array as reference time, replacing the recognition ending time of the previous action recognition time interval with the difference between the reference time and the preset delay time, and replacing the recognition starting time of the next action recognition time interval with the sum of the reference time and the preset delay time;
the data acquisition module is used for acquiring fitness data of a user, performing action recognition on each fitness action according to the fitness data to obtain a recognition result and recording the action ending time of each fitness action;
and the action evaluation module is used for judging whether the action ending time of the current body-building action is greater than the standard ending time, taking the ratio of the difference between the identification ending time and the action ending time to the difference between the identification ending time and the standard ending time as the time score value of the current body-building action when the judgment is yes, and taking the ratio of the difference between the action ending time and the identification starting time to the difference between the standard ending time and the identification starting time as the time score value of the current body-building action when the judgment is not yes.
5. A fitness action criterion evaluation device according to claim 4, wherein the recognition result comprises a force score value;
the action evaluation module is also used for calculating the sum of the product of the time score value and the first weight value of the current body-building action and the product of the strength score value and the second weight value as a standard degree score value;
wherein the sum of the first weight value and the second weight value is 1.
6. The exercise motion standard degree evaluation device of claim 5, wherein the motion evaluation module is further configured to compare the standard degree score value with a plurality of pre-divided score intervals, and take the score corresponding to the score interval where the standard degree score value is located as an evaluation result, wherein the score intervals respectively correspond to different scores.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911058207.3A CN110782967B (en) | 2019-11-01 | 2019-11-01 | Body-building action standard degree assessment method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911058207.3A CN110782967B (en) | 2019-11-01 | 2019-11-01 | Body-building action standard degree assessment method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110782967A true CN110782967A (en) | 2020-02-11 |
| CN110782967B CN110782967B (en) | 2023-04-21 |
Family
ID=69388583
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911058207.3A Active CN110782967B (en) | 2019-11-01 | 2019-11-01 | Body-building action standard degree assessment method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110782967B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111523517A (en) * | 2020-05-26 | 2020-08-11 | 北京奇艺世纪科技有限公司 | Action scoring method and device, electronic equipment and readable storage medium |
| CN112365954A (en) * | 2020-10-26 | 2021-02-12 | 埃欧健身管理(上海)有限公司 | Method and equipment for dynamically adjusting fitness scheme |
| CN113239849A (en) * | 2021-05-27 | 2021-08-10 | 数智引力(厦门)运动科技有限公司 | Fitness action quality evaluation method and system, terminal equipment and storage medium |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6693648B1 (en) * | 2000-11-22 | 2004-02-17 | Campus Crusade For Christ, Inc. | Pointer interactive apparatus |
| US20120316011A1 (en) * | 2011-06-10 | 2012-12-13 | Branko Milosevic | Computer Implemented Athletic Training Method |
| WO2013122327A1 (en) * | 2012-02-17 | 2013-08-22 | 연세대학교 산학협력단 | Physical-fitness test system using acceleration sensor |
| US20130325396A1 (en) * | 2010-09-30 | 2013-12-05 | Fitbit, Inc. | Methods and Systems for Metrics Analysis and Interactive Rendering, Including Events Having Combined Activity and Location Information |
| CN104361207A (en) * | 2010-07-14 | 2015-02-18 | 阿迪达斯股份公司 | Location-aware fitness monitoring systems |
| CN105184382A (en) * | 2015-07-14 | 2015-12-23 | 成都乐动信息技术有限公司 | Optimization method of trajectory and device |
| US20160030804A1 (en) * | 2014-07-31 | 2016-02-04 | Seiko Epson Corporation | Exercise analysis apparatus, exercise analysis method, exercise analysis program, and exercise analysis system |
| US20170203152A1 (en) * | 2016-01-15 | 2017-07-20 | Seiko Epson Corporation | Electronic apparatus, system, analysis method, analysis program, and recording medium |
| WO2017156835A1 (en) * | 2016-03-18 | 2017-09-21 | 深圳大学 | Smart method and system for body building posture identification, assessment, warning and intensity estimation |
| CN107438398A (en) * | 2015-01-06 | 2017-12-05 | 大卫·伯顿 | Portable wearable monitoring system |
| WO2017217567A1 (en) * | 2016-06-15 | 2017-12-21 | (주)그린콤 | Fitness monitoring system |
| CN108346456A (en) * | 2018-01-23 | 2018-07-31 | 曲阜师范大学 | A kind of intelligence sport body building management system |
| CN110020630A (en) * | 2019-04-11 | 2019-07-16 | 成都乐动信息技术有限公司 | Method, apparatus, storage medium and the electronic equipment of assessment movement completeness |
| CN110197721A (en) * | 2019-05-06 | 2019-09-03 | 平安科技（深圳）有限公司 | Tendon condition evaluation method, apparatus and storage medium based on deep learning |
-
2019
- 2019-11-01 CN CN201911058207.3A patent/CN110782967B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6693648B1 (en) * | 2000-11-22 | 2004-02-17 | Campus Crusade For Christ, Inc. | Pointer interactive apparatus |
| CN104361207A (en) * | 2010-07-14 | 2015-02-18 | 阿迪达斯股份公司 | Location-aware fitness monitoring systems |
| US20130325396A1 (en) * | 2010-09-30 | 2013-12-05 | Fitbit, Inc. | Methods and Systems for Metrics Analysis and Interactive Rendering, Including Events Having Combined Activity and Location Information |
| US20120316011A1 (en) * | 2011-06-10 | 2012-12-13 | Branko Milosevic | Computer Implemented Athletic Training Method |
| WO2013122327A1 (en) * | 2012-02-17 | 2013-08-22 | 연세대학교 산학협력단 | Physical-fitness test system using acceleration sensor |
| US20160030804A1 (en) * | 2014-07-31 | 2016-02-04 | Seiko Epson Corporation | Exercise analysis apparatus, exercise analysis method, exercise analysis program, and exercise analysis system |
| CN107438398A (en) * | 2015-01-06 | 2017-12-05 | 大卫·伯顿 | Portable wearable monitoring system |
| CN105184382A (en) * | 2015-07-14 | 2015-12-23 | 成都乐动信息技术有限公司 | Optimization method of trajectory and device |
| US20170203152A1 (en) * | 2016-01-15 | 2017-07-20 | Seiko Epson Corporation | Electronic apparatus, system, analysis method, analysis program, and recording medium |
| WO2017156835A1 (en) * | 2016-03-18 | 2017-09-21 | 深圳大学 | Smart method and system for body building posture identification, assessment, warning and intensity estimation |
| WO2017217567A1 (en) * | 2016-06-15 | 2017-12-21 | (주)그린콤 | Fitness monitoring system |
| CN108346456A (en) * | 2018-01-23 | 2018-07-31 | 曲阜师范大学 | A kind of intelligence sport body building management system |
| CN110020630A (en) * | 2019-04-11 | 2019-07-16 | 成都乐动信息技术有限公司 | Method, apparatus, storage medium and the electronic equipment of assessment movement completeness |
| CN110197721A (en) * | 2019-05-06 | 2019-09-03 | 平安科技（深圳）有限公司 | Tendon condition evaluation method, apparatus and storage medium based on deep learning |
Non-Patent Citations (4)
| Title |
|---|
| FEICHTENHOFER, C.等: "Spatiotemporal Residual Networks for Video Action Recognition [arXiv]" * |
| XIAO F等: "A system for exercise activity recognition and quality evaluation based on green sensing" * |
| 刘刚: "视频监控中人的动作识别" * |
| 董俊峰: "基于视觉的人体运动分析技术研究" * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111523517A (en) * | 2020-05-26 | 2020-08-11 | 北京奇艺世纪科技有限公司 | Action scoring method and device, electronic equipment and readable storage medium |
| CN111523517B (en) * | 2020-05-26 | 2023-08-04 | 北京奇艺世纪科技有限公司 | Action scoring method and device, electronic equipment and readable storage medium |
| CN112365954A (en) * | 2020-10-26 | 2021-02-12 | 埃欧健身管理(上海)有限公司 | Method and equipment for dynamically adjusting fitness scheme |
| CN113239849A (en) * | 2021-05-27 | 2021-08-10 | 数智引力(厦门)运动科技有限公司 | Fitness action quality evaluation method and system, terminal equipment and storage medium |
| CN113239849B (en) * | 2021-05-27 | 2023-12-19 | 数智引力(厦门)运动科技有限公司 | Body-building action quality assessment method, body-building action quality assessment system, terminal equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110782967B (en) | 2023-04-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200314489A1 (en) | System and method for visual-based training | |
| US10512406B2 (en) | Systems and methods for determining an intensity level of an exercise using photoplethysmogram (PPG) | |
| US8113991B2 (en) | Method and system for interactive fitness training program | |
| JP6703199B2 (en) | Operating state evaluation system, operating state evaluation device, operating state evaluation server, operating state evaluation method, and operating state evaluation program | |
| CN110782967A (en) | Fitness action standard degree evaluation method and device | |
| US9174084B2 (en) | Automatic exercise segmentation and recognition | |
| US20170100637A1 (en) | Fitness training guidance system and method thereof | |
| US8951164B2 (en) | Extending gameplay with physical activity monitoring device | |
| US20210299518A1 (en) | Flagging irregularities in user performance in an exercise machine system | |
| CN111477297A (en) | Personal computing device | |
| CN104126185A (en) | Fatigue indices and uses thereof | |
| JPWO2019130527A1 (en) | Extraction program, extraction method and information processing equipment | |
| CN106422208A (en) | Body-building guide method and device based on intelligent wearable device | |
| WO2021195148A1 (en) | Leaderboard with irregularity flags in an exercise machine system | |
| KR102356685B1 (en) | Home training providing system based on online group and method thereof | |
| Kang et al. | The gesture recognition technology based on IMU sensor for personal active spinning | |
| CN111569397B (en) | Handle motion counting method and terminal | |
| WO2023184804A1 (en) | Model control method and apparatus, and device, storage medium and computer program product | |
| CN111589092A (en) | Exercise guidance method and device | |
| CN106178466A (en) | A kind of body-building expenditure analysis method and system | |
| JP2023540286A (en) | Method and system for identifying user behavior | |
| WO2021039857A1 (en) | Video generation device | |
| KR102610165B1 (en) | System for visualizing coutomized motion | |
| Petri et al. | Analysis of anticipatory cues in karate kumite using an in-situ-study | |
| KR20160121460A (en) | Fitness monitoring system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |