CN112057830A - Training method, system, terminal and medium based on multi-dimensional motion capability recognition - Google Patents
Training method, system, terminal and medium based on multi-dimensional motion capability recognition Download PDFInfo
- Publication number
- CN112057830A CN112057830A CN202010947826.4A CN202010947826A CN112057830A CN 112057830 A CN112057830 A CN 112057830A CN 202010947826 A CN202010947826 A CN 202010947826A CN 112057830 A CN112057830 A CN 112057830A
- Authority
- CN
- China
- Prior art keywords
- key
- training
- standard
- motion
- nodes
- 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
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B71/00—Games or sports accessories not covered in groups A63B1/00 - A63B69/00
Landscapes
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Physical Education & Sports Medicine (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a training method based on multi-dimensional motion ability recognition, which has the technical scheme that: constructing an action library consisting of a plurality of standard action data; collecting motion image information of a training object, and correspondingly calibrating key nodes and intermediate nodes in the extracted key frames; simulating and calculating the motion vector of the key frame according to the motion transformation state of the key node in the key frame, and analyzing and calculating the motion vector by referring to the middle node to obtain the flexibility, agility and strength capability value of the training object for practicing the corresponding standard motion; and judging whether the capability value of the training object is qualified according to the standard capability value, and selecting a corresponding video stream from the action library according to the unqualified exercise capability to generate a training plan. Through carrying out multi-dimensional motion ability recognition and analysis on flexibility, agility and strength of the training object, targeted training can be accurately carried out according to defects of the training object, the targeted error of the training is small, and the training effect is remarkably improved.
Description
Technical Field
The invention relates to the technical field of intelligent fitness, in particular to a training method, a training system, a training terminal and a training medium based on multi-dimensional movement ability recognition.
Background
At present the people's internet era, the internet can occupy the most time of life, and along with the acceleration of life rhythm, more and more people's health is in sub-health state simultaneously, but hardly takes time out again and carries out outdoor exercises, and the motion tutor that oneself contrasts on the net at home of most selection carries out the motion body-building, because lack the professional guide, and body-building training effect is not showing, through selecting smart machine to tutor the training. However, in the process of fitness training of a training object, the existing intelligent fitness equipment cannot perform targeted training according to the defects of the training object, and the training purpose error is large, so that the training effect is not ideal. Therefore, how to research and design a training method, a system, a terminal and a medium based on multi-dimensional motion capability recognition is a problem which is urgently needed to be solved at present.
Disclosure of Invention
In order to solve the problems that the existing intelligent fitness equipment cannot be trained in a targeted manner according to the defects of a training object, and the training effect is not ideal due to large training targeted errors, the invention aims to provide a training method, a training system, a training terminal and a training medium based on multi-dimensional movement capability identification.
The technical purpose of the invention is realized by the following technical scheme:
in a first aspect, a training method based on multi-dimensional motion capability recognition is provided, which includes the following steps:
constructing an action library consisting of a plurality of standard action data, wherein each standard action data is divided into a flexibility explanation video stream, an agility training video stream and a strength training video stream;
collecting motion image information of a training object, extracting at least three key frames corresponding to standard actions from the motion image information, correspondingly calibrating key nodes in the key frames, and uniformly distributing intermediate nodes between adjacent key nodes;
simulating and calculating the motion vector of the key frame according to the motion transformation state of the key node in the key frame, and analyzing and calculating the motion vector by referring to the middle node to obtain the flexibility, agility and strength capability value of the training object for practicing the corresponding standard motion;
and judging whether the capability value of the training object is qualified according to the standard capability value, and selecting a corresponding video stream from the action library according to the unqualified exercise capability to generate a training plan.
Further, the analysis and calculation of the flexibility ability value are specifically as follows:
constructing a spatial motion curve graph according to the motion vectors of the key nodes in the key frame;
stretching or compressing the space dynamic curve graph according to the ratio of the number of intermediate nodes between key nodes in the current key frame to the number of intermediate nodes between key nodes in the standard key frame to obtain a space simulation curve graph;
comparing and analyzing the space simulation curve graph and the standard space curve graph, and calculating to obtain the displacement offset of the key node on the key frame time axis;
and (4) calculating to obtain the flexibility force value of the key node after the integral error elimination is carried out on the displacement offset according to the standard displacement error.
Further, the analysis and calculation of the capability value of the agility degree specifically includes:
calculating the displacement of the key node in the current key frame and the key node in the standard key frame according to the space simulation curve graph and the standard space curve graph;
calculating the movement rate of the key nodes in each time period according to the time axis of the key frame;
and (4) calculating to obtain the agility capability value of the key node after the integral error of the motion rate is eliminated according to the standard rate error.
Further, the analysis and calculation of the ability value of the strength are specifically as follows:
collecting at least one fluctuation frame before and after a current key frame on a key frame time axis according to a preset time interval;
calculating corresponding amplitude and vibration frequency according to the motion vectors of the key nodes in the current key frame and the fluctuation frame;
and generating a fluctuation curve graph according to the amplitude and the vibration frequency, and analyzing the fluctuation curve graph to obtain a strength capability value of the key node, which represents the stability.
In a second aspect, a training system based on multi-dimensional motion capability recognition is provided, including:
the action library construction module is used for constructing an action library consisting of a plurality of standard action data, and each standard action data is divided into a flexibility explanation video stream, an agility training video stream and a strength training video stream;
the image processing module is used for acquiring motion image information of a training object, extracting at least three key frames corresponding to standard actions from the motion image information, correspondingly calibrating key nodes in the key frames and at least one middle node positioned between adjacent key nodes;
the capability value calculation module is used for simulating and calculating the motion vector of the key frame according to the motion transformation states of the key nodes and the intermediate nodes in the key frame, and analyzing and calculating the motion vector to obtain the capability values of the training object for practicing the flexibility, the agility and the strength of the corresponding standard motion;
and the plan generation module is used for judging whether the capability value of the training object is qualified according to the standard capability value and generating a training plan after selecting a corresponding video stream from the action library according to the unqualified exercise capability.
Furthermore, the capability value calculation module comprises a flexibility sub-module consisting of a space curve unit, a simulation curve unit, a displacement offset calculation unit and a flexibility calculation unit;
the spatial curve unit is used for constructing a spatial motion curve graph according to the motion vectors of the key nodes in the key frame;
the simulation curve unit is used for stretching or compressing the space dynamic curve graph according to the ratio of the number of the middle nodes between the key nodes in the current key frame to the number of the middle nodes between the key nodes in the standard key frame to obtain a space simulation curve graph;
the displacement offset calculation unit is used for comparing and analyzing the space simulation curve graph and the standard space curve graph and calculating to obtain the displacement offset of the key node on the time axis of the key frame;
and the flexibility calculation unit is used for calculating the flexibility performance value of the key node after the integral error of the displacement offset is eliminated according to the standard displacement error.
Furthermore, the capability value calculating module also comprises an agility submodule consisting of a displacement calculating unit, a speed calculating unit and an agility calculating unit;
the displacement calculating unit is used for calculating the displacement of the key node in the current key frame and the key node in the standard key frame according to the space simulation curve graph and the standard space curve graph;
the rate calculation unit is used for calculating the motion rate of the key nodes in each time period according to the time axis of the key frame;
and the agility computing unit is used for computing the agility capability value of the key node after the integral error of the motion rate is eliminated according to the standard rate error.
Furthermore, the capability value calculation module also comprises a force submodule consisting of an acquisition unit, a fluctuation calculation unit and a force calculation unit;
the acquisition unit is used for acquiring at least one fluctuation frame before and after the current key frame on the key frame time axis according to a preset time interval;
the fluctuation calculating unit is used for calculating corresponding amplitude and vibration frequency according to the current key frame and the motion vector of the key node in the fluctuation frame;
and the force calculation unit is used for generating a fluctuation curve graph according to the amplitude and the vibration frequency, and analyzing the fluctuation curve graph to obtain a force capacity value of the key node, wherein the force capacity value represents the stability.
In a third aspect, a computer terminal is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the program, the processor implements the training method based on multi-dimensional motion capability recognition according to any one of the first aspect.
In a fourth aspect, a computer-readable medium is provided, on which a computer program is stored, the computer program being executed by a processor to implement the training method based on multi-dimensional motion capability recognition according to any one of the first aspect.
Compared with the prior art, the invention has the following beneficial effects:
1. according to the invention, through carrying out multi-dimensional movement ability recognition and analysis on the flexibility, agility and strength of the training object, targeted training can be accurately carried out according to the defects of the training object, the targeted error of the training is small, and the training effect is obviously improved;
2. according to the invention, through the calibration of the key nodes and the intermediate nodes, the motion abilities of different training objects are simulated into the objects matched with the standard training objects according to the ratio of the number of the actual intermediate nodes to the number of the standard nodes, so that the calculation accuracy is improved in the process of motion ability calculation and analysis, and the situation that people of different ages, heights and body types have large errors in the process of motion ability identification is avoided.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
FIG. 1 is an overall flow chart in an embodiment of the present invention;
FIG. 2 is a flowchart of calculation of a flexibility force value in the embodiment of the present invention;
FIG. 3 is a flow chart of agility capability value calculation in an embodiment of the invention;
FIG. 4 is a flow chart of force capability value calculation in an embodiment of the present invention;
fig. 5 is a system architecture diagram in an embodiment of the invention.
Reference numbers and corresponding part names in the drawings:
101. an action library construction module; 102. an image processing module; 103. a capability value calculation module; 104. a plan generation module; 201. a flexibility sub-module; 202. a space curve unit; 203. a simulation curve unit; 204. a displacement offset calculation unit; 205. a flexible computing unit; 301. an agility sub-module; 302. a displacement amount calculation unit; 303. a rate calculation unit; 304. an agility calculation unit; 401. a strength submodule; 402. a collection unit; 403. a fluctuation calculation unit; 404. a force calculation unit.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail in the following with reference to examples 1-2 and accompanying fig. 1-5, and the exemplary embodiments and descriptions thereof are only used for explaining the present invention and are not to be construed as limiting the present invention.
Example 1: the training method based on multi-dimensional motion ability recognition, as shown in fig. 1, includes the following steps:
s101: and constructing an action library consisting of a plurality of standard action data, wherein each standard action data is divided into a flexibility explanation video stream, an agility training video stream and a strength training video stream.
S102: the method comprises the steps of collecting motion image information of a training object, extracting at least three key frames corresponding to standard actions from the motion image information, correspondingly calibrating key nodes in the key frames, and uniformly distributing middle nodes between adjacent key nodes.
S103: and simulating and calculating the motion vector of the key frame according to the motion transformation state of the key node in the key frame, and analyzing and calculating the motion vector by referring to the middle node to obtain the flexibility, agility and strength capability value of the training object for practicing the corresponding standard motion.
S104: and judging whether the capability value of the training object is qualified according to the standard capability value, and selecting a corresponding video stream from the action library according to the unqualified exercise capability to generate a training plan.
In S103, as shown in fig. 2, the ability value analysis calculation of flexibility is specifically:
s201: and constructing a spatial motion curve graph according to the motion vectors of the key nodes in the key frame.
S202: and stretching or compressing the space dynamic curve graph according to the ratio of the number of the intermediate nodes between the key nodes in the current key frame to the number of the intermediate nodes between the key nodes in the standard key frame to obtain a space simulation curve graph.
S203: and comparing and analyzing the space simulation curve graph and the standard space curve graph, and calculating to obtain the displacement offset of the key node on the key frame time axis.
S204: and (4) calculating to obtain the flexibility force value of the key node after the integral error elimination is carried out on the displacement offset according to the standard displacement error.
In S103, as shown in fig. 4, the agility ability value analysis and calculation specifically includes:
s301: and calculating the displacement of the key node in the current key frame and the key node in the standard key frame according to the space simulation curve graph and the standard space curve graph.
S302: and calculating the movement rate of the key nodes in each time period according to the time axis of the key frame.
S303: and (4) calculating to obtain the agility capability value of the key node after the integral error of the motion rate is eliminated according to the standard rate error.
In S103, as shown in fig. 4, the ability value analysis and calculation of the strength is specifically as follows:
s401: and acquiring at least one fluctuation frame before and after the current key frame on the key frame time axis according to a preset time interval.
S402: and calculating corresponding amplitude and vibration frequency according to the motion vectors of the key nodes in the current key frame and the fluctuation frame.
S403: and generating a fluctuation curve graph according to the amplitude and the vibration frequency, and analyzing the fluctuation curve graph to obtain a strength capability value of the key node, which represents the stability.
Example 2: the training system based on multi-dimensional motion ability recognition, as shown in fig. 5, includes an action library construction module 101, an image processing module 102, an ability value calculation module 103, and a plan generation module 104. The action library construction module 101 constructs an action library composed of a plurality of standard action data, and each standard action data is divided into a flexibility explanation video stream, an agility training video stream, and a strength training video stream. The image processing module 102 collects motion image information of a training object, extracts at least three key frames corresponding to standard actions from the motion image information, and at least one middle node located between adjacent key nodes and corresponding to a calibration key node in the key frames. The ability value calculation module 103 is used for calculating the motion vector of the key frame according to the motion transformation state simulation of the key node and the middle node in the key frame, and analyzing and calculating the motion vector to obtain the ability value of the training object for practicing the flexibility, agility and strength of the corresponding standard motion. And the plan generating module 104 is used for judging whether the capability value of the training object is qualified according to the standard capability value, and generating a training plan after selecting a corresponding video stream from the action library according to the unqualified exercise capability.
The capability value calculation module 103 comprises a flexibility submodule 201 which is composed of a space curve unit 202, a simulation curve unit 203, a displacement offset calculation unit 204 and a flexibility calculation unit 205. The spatial curve unit 202 is configured to construct a spatial motion curve graph according to the motion vectors of the key nodes in the key frame. And the simulation curve unit 203 is configured to stretch or compress the spatial dynamic curve graph according to a ratio of the number of intermediate nodes between the key nodes in the current key frame to the number of intermediate nodes between the key nodes in the standard key frame to obtain a spatial simulation curve graph. And the displacement offset calculation unit 204 is configured to compare and analyze the spatial simulation graph and the standard spatial graph, and calculate to obtain a displacement offset of the key node on the time axis of the key frame. And the flexibility calculation unit 205 is used for calculating the flexibility performance value of the key node after the integral error of the displacement offset is eliminated according to the standard displacement error.
The capability value calculating module 103 further includes an agility sub-module 301 composed of a displacement calculating unit 302, a rate calculating unit 303, and an agility calculating unit 304. The displacement calculating unit 302 is configured to calculate displacements of the key node in the current key frame and the key node in the standard key frame according to the spatial simulation graph and the standard spatial graph. And the rate calculating unit 303 is configured to calculate a motion rate of the key node in each time segment according to the key frame time axis. And the agility calculating unit 304 is configured to calculate an agility capability value of the key node after performing overall error elimination on the motion rate according to the standard rate error.
The capability value calculation module 103 further includes a force submodule 401, which is composed of an acquisition unit 402, a fluctuation calculation unit 403, and a force calculation unit 404. The acquiring unit 402 is configured to acquire at least one fluctuation frame before and after a current key frame on the key frame time axis according to a predetermined time interval. And a fluctuation calculating unit 403, configured to calculate corresponding amplitude and vibration frequency according to the current key frame and the motion vector of the key node in the fluctuation frame. And the force calculating unit 404 is used for generating a fluctuation curve graph according to the amplitude and the vibration frequency, and obtaining a force capacity value of the key node, which represents the stability, by analyzing the fluctuation curve graph.
The working principle is as follows: through carrying out multi-dimensional motion capability identification and analysis on the flexibility, agility and strength of the training object, targeted training can be accurately carried out according to the defects of the training object, the targeted error of the training is small, and the training effect is remarkably improved; through the calibration of key nodes and intermediate nodes, the exercise capacity of different training objects is simulated into an object matched with a standard training object according to the ratio of the number of the actual intermediate nodes to the number of the standard nodes, the calculation accuracy is improved in the process of calculating and analyzing the exercise capacity, and the situation that people of different ages, heights and body types have large errors in the process of identifying the exercise capacity is avoided.
The above embodiments are provided to further explain the objects, technical solutions and advantages of the present invention in detail, it should be understood that the above embodiments are merely exemplary embodiments of the present invention and are not intended to limit the scope of the present invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. The training method based on the multi-dimensional movement ability recognition is characterized by comprising the following steps of:
constructing an action library consisting of a plurality of standard action data, wherein each standard action data is divided into a flexibility explanation video stream, an agility training video stream and a strength training video stream;
collecting motion image information of a training object, extracting at least three key frames corresponding to standard actions from the motion image information, correspondingly calibrating key nodes in the key frames, and uniformly distributing intermediate nodes between adjacent key nodes;
simulating and calculating the motion vector of the key frame according to the motion transformation state of the key node in the key frame, and analyzing and calculating the motion vector by referring to the middle node to obtain the flexibility, agility and strength capability value of the training object for practicing the corresponding standard motion;
and judging whether the capability value of the training object is qualified according to the standard capability value, and selecting a corresponding video stream from the action library according to the unqualified exercise capability to generate a training plan.
2. The training method based on multi-dimensional movement capability identification as claimed in claim 1, wherein the capability value analysis calculation of flexibility is specifically as follows:
constructing a spatial motion curve graph according to the motion vectors of the key nodes in the key frame;
stretching or compressing the space dynamic curve graph according to the ratio of the number of intermediate nodes between key nodes in the current key frame to the number of intermediate nodes between key nodes in the standard key frame to obtain a space simulation curve graph;
comparing and analyzing the space simulation curve graph and the standard space curve graph, and calculating to obtain the displacement offset of the key node on the key frame time axis;
and (4) calculating to obtain the flexibility force value of the key node after the integral error elimination is carried out on the displacement offset according to the standard displacement error.
3. The training method based on multi-dimensional athletic ability recognition as claimed in claim 2, wherein the ability value analysis and calculation of agility is specifically:
calculating the displacement of the key node in the current key frame and the key node in the standard key frame according to the space simulation curve graph and the standard space curve graph;
calculating the movement rate of the key nodes in each time period according to the time axis of the key frame;
and (4) calculating to obtain the agility capability value of the key node after the integral error of the motion rate is eliminated according to the standard rate error.
4. The training method based on multi-dimensional athletic ability recognition as claimed in claim 1, wherein the ability value analysis and calculation of the strength is specifically:
collecting at least one fluctuation frame before and after a current key frame on a key frame time axis according to a preset time interval;
calculating corresponding amplitude and vibration frequency according to the motion vectors of the key nodes in the current key frame and the fluctuation frame;
and generating a fluctuation curve graph according to the amplitude and the vibration frequency, and analyzing the fluctuation curve graph to obtain a strength capability value of the key node, which represents the stability.
5. Training system based on multidimension degree motion ability discernment, characterized by includes:
the action library construction module (101) is used for constructing an action library consisting of a plurality of standard action data, and each standard action data is divided into a flexibility explanation video stream, an agility training video stream and a strength training video stream;
the image processing module (102) is used for acquiring motion image information of a training object, extracting at least three key frames corresponding to standard actions from the motion image information, correspondingly calibrating key nodes in the key frames and at least one middle node positioned between adjacent key nodes;
the ability value calculation module (103) is used for simulating and calculating the motion vector of the key frame according to the motion transformation states of the key nodes and the middle nodes in the key frame, and analyzing and calculating the motion vector to obtain the flexibility, agility and strength ability values of the training object for practicing the corresponding standard motions;
and the plan generation module (104) judges whether the capability value of the training object is qualified according to the standard capability value, and generates a training plan after selecting a corresponding video stream from the action library according to the unqualified exercise capability.
6. The training system based on multi-dimensional movement capability identification as claimed in claim 5, wherein the capability value calculation module (103) comprises a flexibility sub-module (201) composed of a space curve unit (202), a simulation curve unit (203), a displacement offset calculation unit (204) and a flexibility calculation unit (205);
the spatial curve unit (202) is used for constructing a spatial motion curve graph according to the motion vectors of the key nodes in the key frame;
the simulation curve unit (203) is used for stretching or compressing the space dynamic curve graph according to the ratio of the number of the middle nodes between the key nodes in the current key frame to the number of the middle nodes between the key nodes in the standard key frame to obtain a space simulation curve graph;
the displacement offset calculation unit (204) is used for comparing and analyzing the space simulation curve graph and the standard space curve graph, and calculating to obtain the displacement offset of the key node on the time axis of the key frame;
and the flexibility calculation unit (205) is used for calculating the flexibility performance value of the key node after the integral error elimination of the displacement offset according to the standard displacement error.
7. The multi-dimensional athletic ability recognition-based training system according to claim 6, wherein the ability value calculation module (103) further comprises an agility sub-module (301) consisting of a displacement amount calculation unit (302), a rate calculation unit (303), and an agility calculation unit (304);
a displacement calculation unit (302) for calculating displacements of key nodes in the current key frame and key nodes in the standard key frame according to the spatial simulation graph and the standard spatial graph;
the rate calculation unit (303) is used for calculating the motion rate of the key nodes in each time period according to the time axis of the key frame;
and the agility computing unit (304) is used for computing the agility capability value of the key node after the motion rate is subjected to overall error elimination according to the standard rate error.
8. The training system based on multi-dimensional motion capability identification as claimed in claim 5, wherein the capability value calculation module (103) further comprises a force sub-module (401) composed of an acquisition unit (402), a fluctuation calculation unit (403) and a force calculation unit (404);
the device comprises an acquisition unit (402) for acquiring at least one fluctuation frame before and after a current key frame on a key frame time axis according to a preset time interval;
the fluctuation calculating unit (403) is used for calculating corresponding amplitude and vibration frequency according to the current key frame and the motion vector of the key node in the fluctuation frame;
and the force calculation unit (404) is used for generating a fluctuation curve graph according to the amplitude and the vibration frequency, and obtaining a force capacity value of the key node, which represents the stability, by analyzing the fluctuation curve graph.
9. A computer terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the training method based on multi-dimensional motion capability recognition according to any one of claims 1 to 4 when executing the program.
10. A computer-readable medium, on which a computer program is stored, the computer program being executed by a processor to implement the training method based on multi-dimensional athletic performance recognition according to any one of claims 1-4.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010947826.4A CN112057830B (en) | 2020-09-10 | 2020-09-10 | Training method, system, terminal and medium based on multi-dimensional motion capability recognition |
| PCT/CN2021/129533 WO2022053080A2 (en) | 2020-09-10 | 2021-11-09 | Training method and system based on multi-dimensional movement ability recognition, terminal, and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010947826.4A CN112057830B (en) | 2020-09-10 | 2020-09-10 | Training method, system, terminal and medium based on multi-dimensional motion capability recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112057830A true CN112057830A (en) | 2020-12-11 |
| CN112057830B CN112057830B (en) | 2021-07-27 |
Family
ID=73663632
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010947826.4A Active CN112057830B (en) | 2020-09-10 | 2020-09-10 | Training method, system, terminal and medium based on multi-dimensional motion capability recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112057830B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022053080A3 (en) * | 2020-09-10 | 2022-04-28 | 成都拟合未来科技有限公司 | Training method and system based on multi-dimensional movement ability recognition, terminal, and medium |
| CN117438040A (en) * | 2023-12-22 | 2024-01-23 | 亿慧云智能科技（深圳）股份有限公司 | Exercise course self-adaptive configuration method, device, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150199917A1 (en) * | 2012-11-12 | 2015-07-16 | Barry J. French | Fitness assessment method and system |
| CN110448870A (en) * | 2019-08-16 | 2019-11-15 | 深圳特蓝图科技有限公司 | A kind of human body attitude training method |
| CN110728220A (en) * | 2019-09-30 | 2020-01-24 | 上海大学 | Gymnastics auxiliary training method based on human body action skeleton information |
| CN111046766A (en) * | 2019-12-02 | 2020-04-21 | 武汉烽火众智数字技术有限责任公司 | Behavior recognition method and device and computer storage medium |
-
2020
- 2020-09-10 CN CN202010947826.4A patent/CN112057830B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150199917A1 (en) * | 2012-11-12 | 2015-07-16 | Barry J. French | Fitness assessment method and system |
| CN110448870A (en) * | 2019-08-16 | 2019-11-15 | 深圳特蓝图科技有限公司 | A kind of human body attitude training method |
| CN110728220A (en) * | 2019-09-30 | 2020-01-24 | 上海大学 | Gymnastics auxiliary training method based on human body action skeleton information |
| CN111046766A (en) * | 2019-12-02 | 2020-04-21 | 武汉烽火众智数字技术有限责任公司 | Behavior recognition method and device and computer storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022053080A3 (en) * | 2020-09-10 | 2022-04-28 | 成都拟合未来科技有限公司 | Training method and system based on multi-dimensional movement ability recognition, terminal, and medium |
| CN117438040A (en) * | 2023-12-22 | 2024-01-23 | 亿慧云智能科技（深圳）股份有限公司 | Exercise course self-adaptive configuration method, device, equipment and storage medium |
| CN117438040B (en) * | 2023-12-22 | 2024-04-05 | 亿慧云智能科技（深圳）股份有限公司 | Exercise course self-adaptive configuration method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112057830B (en) | 2021-07-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112057830B (en) | Training method, system, terminal and medium based on multi-dimensional motion capability recognition | |
| WO2022053080A2 (en) | Training method and system based on multi-dimensional movement ability recognition, terminal, and medium | |
| CN111860157A (en) | Motion analysis method, device, equipment and storage medium | |
| US20230154607A1 (en) | Methods and systems for identifying user action | |
| CN111507301B (en) | Video processing method, video processing device, computer equipment and storage medium | |
| CN110693500B (en) | Balance ability exercise evaluation method, device, server and storage medium | |
| WO2021217947A1 (en) | Handle type exercise counting method and terminal | |
| JP2020048827A (en) | Information processing device, support method, and support system | |
| Xu et al. | Likert scoring with grade decoupling for long-term action assessment | |
| CN113856132B (en) | Rope skipping action recognition system and method and rope skipping | |
| CN113392743B (en) | Abnormal action detection method, abnormal action detection device, electronic equipment and computer storage medium | |
| CN116186561B (en) | Running gesture recognition and correction method and system based on high-dimensional time sequence diagram network | |
| CN113262459A (en) | Method, apparatus and medium for determining motion standard of sport body-building mirror | |
| CN111985853A (en) | Interactive practice ranking evaluation method, system, terminal and medium | |
| CN111685773A (en) | Pregnant woman movement monitoring method and device, computer equipment and storage medium | |
| CN116152924A (en) | Motion gesture evaluation method, device and system and computer storage medium | |
| CN112040301A (en) | Interactive exercise equipment action explanation method, system, terminal and medium | |
| CN112257642B (en) | Human body continuous motion similarity evaluation method and evaluation device | |
| Zhao et al. | [Retracted] The Design of the Exercise Load Monitoring System Based on Internet of Things | |
| CN115813377B (en) | Intelligent posture assessment method and system | |
| CN117577332B (en) | Rehabilitation evaluation method and system based on visual analysis | |
| Liang et al. | Research on Fitness Action Evaluation System Based on Skeleton | |
| CN116306766B (en) | Wisdom horizontal bar pull-up examination training system based on skeleton recognition technology | |
| Bi et al. | LAZIER: A Virtual Fitness Coach Based on AI Technology | |
| CN117058758A (en) | Intelligent sports examination method based on AI technology and related device |
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 |