CN111259716A - Human body running posture identification and analysis method and device based on computer vision - Google Patents
Human body running posture identification and analysis method and device based on computer vision Download PDFInfo
- Publication number
- CN111259716A CN111259716A CN201910985432.5A CN201910985432A CN111259716A CN 111259716 A CN111259716 A CN 111259716A CN 201910985432 A CN201910985432 A CN 201910985432A CN 111259716 A CN111259716 A CN 111259716A
- Authority
- CN
- China
- Prior art keywords
- posture
- running
- standard
- motion trail
- computer vision
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 41
- 230000033001 locomotion Effects 0.000 claims abstract description 74
- 238000010586 diagram Methods 0.000 claims abstract description 29
- 238000012937 correction Methods 0.000 claims abstract description 20
- 238000012360 testing method Methods 0.000 claims abstract description 15
- 238000000034 method Methods 0.000 claims abstract description 14
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 8
- 230000036544 posture Effects 0.000 claims description 195
- 238000012549 training Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 8
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims 2
- 230000000694 effects Effects 0.000 abstract description 2
- 208000025978 Athletic injury Diseases 0.000 abstract 1
- 206010041738 Sports injury Diseases 0.000 abstract 1
- 230000009471 action Effects 0.000 description 3
- 230000006378 damage Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06V40/23—Recognition of whole body movements, e.g. for sport training
- G06V40/25—Recognition of walking or running movements, e.g. gait recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The human body running gesture recognition analysis method based on computer vision comprises the steps of carrying out camera shooting collection on data of a tester on a running machine through a camera, carrying out data classification, and obtaining a gesture recognition model by adopting a convolutional neural network method; and then, shooting the running posture of the test object, comparing the running posture with a standard posture motion trail diagram for operation, and outputting a posture standard degree score and a correction suggestion. The specific error position and the non-standard type of the test object are corrected, the probability of sports injury caused by the test object is reduced, and a better body-building effect is achieved.
Description
Technical Field
The invention relates to the technical field of computer vision image recognition, in particular to a method and a device for recognizing and analyzing a running gesture.
Background
The human body action recognition through the computer vision has important practical significance, wide application prospect and considerable economic value, the intelligent device obtains the ability of understanding the world, the requirements of various artificial intelligence applications can be met, and the human body action recognition device can also play a promoting role and a reference value in human self-cognition. The application field related to human body action recognition through computer vision mainly comprises: the system comprises an intelligent monitoring system, video storage and retrieval, an intelligent human-computer interface, a safe home environment and motion analysis.
The motion analysis mainly tracks the motion of human joint parts in a computer vision mode, establishes a human body geometric model, analyzes the human body motion, is beneficial to mastering the motion state of a human body and improves the motion performance. In particular, in sports such as sports and dancing, an athlete can correct the posture and the like by analyzing the movement of a person, which is helpful for improving the performance. The rehabilitation status of the patient can be observed through the movement posture in medicine, and the treatment scheme is adjusted.
The total scale of national sports consumption reaches 1.5 trillion yuan in 2020, the proportion of per capita sports consumption expense in the total consumption expense is obviously increased, and the sports consumption structure is more reasonable. On specific tasks, the document mentions that the detailed implementation of the development plan of the marathon project industry is mainly supported and promoted, and a new sports consumption hotspot is formed. The time is as short as 5 years from 2014 to 2018, the marathon events in China are increased from 50 to 1000, and the number growth rate reaches 2000%. Although the number of marathon events and the number of participants are increasing in a blowout manner, the quality of the events is greatly improved, but the popularity of popular players is low. The most serious and common problem among the popular players is the lack of standardization of running postures, which leads to various serious injuries and diseases. Therefore, the running posture analysis method has great significance for the popular marathon players to run through computer vision and provide instructive opinions for the popular marathon players.
Therefore, the applicant has conducted a study of a human body running posture recognition analysis technique based on computer vision for the running posture specification of a general runner.
Disclosure of Invention
In order to solve the problems, the invention provides a human body running posture identification and analysis method and a device based on computer vision, which take video as a medium and adopt a method based on computer vision to quickly and accurately identify the normative running posture.
In order to achieve the purpose, the invention adopts the following technical scheme:
the human body running posture identification and analysis method based on computer vision comprises the following steps:
acquiring data, shooting various typical wrong running postures and standard running postures on a running machine, and drawing a running posture movement track graph of the shot object with the height of 170 cm;
step two, data classification, namely performing posture classification on the running posture motion trail diagram obtained in the step one;
step three, data training, namely, performing recognition training on the pictures subjected to posture classification in the step two by adopting a convolutional neural network method, performing grouping training on the motion trail pictures according to standard running postures and various typical error running postures to obtain a running posture recognition model group corresponding to the standard running postures and obtain a posture recognition model;
step four, gesture recognition, namely shooting the running gesture of the test object, searching and recognizing the running gesture movement locus diagram of the test object in the real-time video through the gesture recognition model obtained in the step three, and confirming the user gesture which is consistent with the gesture classification in the gesture recognition model;
and step five, evaluating and analyzing the posture, comparing the user posture identified in the step four with a standard posture motion trail diagram through a posture identification model, and outputting a posture standard degree score and a correction opinion.
According to the human body running gesture recognition and analysis method based on computer vision, the data acquisition comprises gesture shooting, video uploading, video preprocessing and motion trail drawing;
the speed of the treadmill is a fixed value when the posture is shot;
the data acquisition is used for shooting standard posture runners and various typical non-standard posture runners at a plurality of specified angles;
uploading a running video shot in real time to video processing software;
video preprocessing, including dryness removal, video segmentation, key frame extraction and feature extraction;
drawing a motion trail graph, and drawing a running posture motion trail graph according to the motion trail of the mark points of each part of the body of the tested object in the video;
and when the motion trail graph is drawn, scaling the running posture motion trail graph into a running posture motion trail graph with the specified height of 170cm according to the height of the tested object in the video.
In the human body running posture identification and analysis method based on computer vision, when data is collected, body parts of a user, such as the head, the shoulders, the hands, the upper arm, the lower arm, the elbows, the trunk, the hips and the like, are marked and shot.
In the human body running posture identification and analysis method based on computer vision, the posture in the step two is classified, and data are divided into standard running postures and non-standard running postures; the nonstandard running postures are divided into the conditions that the left-right and up-down swinging amplitudes of the head, the trunk and the hip are too large, and the front-back, left-right and up-down swinging amplitudes of the shoulder, the hand, the upper arm, the lower arm and the elbow are too large and the left-right and left-right are asymmetric.
In the human body running posture identification and analysis method based on computer vision, the four steps of posture identification are carried out, and running posture identification is carried out on each calibration part of the body of the tested object according to the running posture identification model.
In the human body running posture identification and analysis method based on computer vision, the five-step posture evaluation and analysis is carried out, grade scores with different deviation degrees are set according to the standard running posture motion trail diagram, and standard grade scores and correction opinions are output through the comparison operation of the tested object running posture motion trail diagram and the standard running posture motion trail diagram.
Human body running posture recognition and analysis device based on computer vision is characterized in that:
the system comprises a treadmill and a camera, and is used for shooting a test object on the treadmill;
the cloud computing module is used for drawing a running posture motion trail diagram, carrying out convolutional neural network training on typical error running postures and standard running postures to obtain a posture recognition model, identifying the running posture type of the tested object, carrying out comparison operation on the tested object, and outputting a posture standard degree score and a correction suggestion;
the back-end processing module is used for storing the posture standard degree score and the correction suggestion obtained by the human body running posture recognition analysis method based on computer vision;
and the intelligent terminal is used for downloading the posture standard degree score and the correction opinion from the back-end processing module.
The invention has the following advantages:
expensive equipment is not needed for runners, and the cost is controllable; the running posture recognition method is characterized in that a tested object is only required to be tested on a running machine with a specified speed, the running posture is shot from each specified angle, the running posture standardization recognition analysis is carried out by adopting a computer vision-based method, a recognition model can be edited, an accurate running posture recognition result can be provided, an accurate running posture movement track graph is generated for a tester, specific error positions and non-standard types of the tester are corrected, the probability of movement damage caused by the tester is reduced, and a better body building effect is achieved.
Drawings
Figure 1 is a graph of a standard running posture elbow motion trajectory.
Fig. 2 is a diagram of a typical wrong-running motion trajectory of excessive elbow swing amplitude.
Fig. 3 is a schematic structural diagram of a human running posture recognition and analysis device based on computer vision.
Detailed Description
The invention firstly provides a human body running posture identification and analysis method based on computer vision, which takes a real-time video as a medium and adopts a method based on computer vision to carry out the normative identification of the running posture.
The human body running posture identification and analysis method based on computer vision comprises the following steps:
acquiring data, shooting various typical wrong running postures and standard running postures on a running machine, and drawing a running posture movement track graph of the shot object with the height of 170 cm;
step two, data classification, namely performing posture classification on the running posture motion trail diagram obtained in the step one;
step three, data training, namely, performing recognition training on the pictures subjected to posture classification in the step two by adopting a convolutional neural network method, performing grouping training on the motion trail pictures according to standard running postures and various typical error running postures to obtain a running posture recognition model group corresponding to the standard running postures and obtain a posture recognition model;
step four, gesture recognition, namely shooting the running gesture of the test object, searching and recognizing the running gesture movement locus diagram of the test object in the real-time video through the gesture recognition model obtained in the step three, and confirming the user gesture which is consistent with the gesture classification in the gesture recognition model;
and step five, evaluating and analyzing the posture, comparing the user posture identified in the step four with a standard posture motion trail diagram through a posture identification model, and outputting a posture standard degree score and a correction opinion.
According to the human body running gesture recognition and analysis method based on computer vision, the data acquisition comprises gesture shooting, video uploading, video preprocessing and motion trail drawing;
the speed of the treadmill is a fixed value when the posture is shot;
the data acquisition is used for shooting standard posture runners and various typical non-standard posture runners at a plurality of specified angles;
uploading a running video shot in real time to video processing software;
video preprocessing, including dryness removal, video segmentation, key frame extraction and feature extraction;
drawing a motion trail graph, and drawing a running posture motion trail graph according to the motion trail of the mark points of each part of the body of the tested object in the video;
and when the motion trail graph is drawn, scaling the running posture motion trail graph into a running posture motion trail graph with the specified height of 170cm according to the height of the tested object in the video.
In the human body running posture identification and analysis method based on computer vision, when data is collected, body parts of a user, such as the head, the shoulders, the hands, the upper arm, the lower arm, the elbows, the trunk, the hips and the like, are marked and shot.
In the human body running posture identification and analysis method based on computer vision, the posture in the step two is classified, and data are divided into standard running postures and non-standard running postures; the nonstandard running postures are divided into the conditions that the left-right and up-down swinging amplitudes of the head, the trunk and the hip are too large, and the front-back, left-right and up-down swinging amplitudes of the shoulder, the hand, the upper arm, the lower arm and the elbow are too large and the left-right and left-right are asymmetric.
In the human body running posture identification and analysis method based on computer vision, the four steps of posture identification are carried out, and running posture identification is carried out on each calibration part of the body of the tested object according to the running posture identification model.
In the human body running posture identification and analysis method based on computer vision, the five-step posture evaluation and analysis is carried out, grade scores with different deviation degrees are set according to the standard running posture motion trail diagram, and standard grade scores and correction opinions are output through the comparison operation of the tested object running posture motion trail diagram and the standard running posture motion trail diagram.
Human body running posture recognition and analysis device based on computer vision is characterized in that:
the system comprises a treadmill and a camera, and is used for shooting a test object on the treadmill;
the cloud computing module is used for drawing a running posture motion trail diagram, carrying out convolutional neural network training on typical error running postures and standard running postures to obtain a posture recognition model, identifying the running posture type of the tested object, carrying out comparison operation on the tested object, and outputting a posture standard degree score and a correction suggestion;
the back-end processing module is used for storing the posture standard degree score and the correction suggestion obtained by the human body running posture recognition analysis method based on computer vision;
and the intelligent terminal is used for downloading the posture standard degree score and the correction opinion from the back-end processing module.
The specific process of identifying the tester image in the real-time video comprises the following steps: firstly, image preprocessing is carried out, irrelevant information in the image is eliminated, useful real information is recovered, the detectability of the relevant information is enhanced, and data is simplified to the maximum extent; then, carrying out motion tracking according to the calibration points to obtain a running posture trajectory diagram; then, identifying the running posture by adopting a running posture identification model; and finally, obtaining the standard grade and the correction suggestion according to the recognition result.
Taking an elbow as an example, firstly, marking the left elbow and the right elbow of a tested object, then arranging the tested object to normally run on a running machine at a specified speed, and shooting at specified distance positions from two sides of the tested object by using cameras respectively to obtain running posture test videos of the tested object.
Uploading the running posture test video of the tested person to video processing software, and firstly carrying out dryness removal, video segmentation, key frame extraction and feature extraction through video preprocessing. Then obtaining the motion trail maps of the left and right elbows by the motion tracking technology, and finally scaling the motion trail maps into a running posture curve map with the specified height of 170cm, wherein the proportion is 170/.
And directly inputting a motion trail diagram of the tested object into the trained running posture identification model, wherein a standard running posture elbow motion trail is shown in figure 1, and a typical error running posture elbow motion trail is shown in figure 2. The output result has the following conditions:
A. if the left and right elbow motion trail images of the tested object are as shown in figure 1, the standard running posture is judged.
B. If the ordinate of the left end point of the motion trail diagram of the left elbow and the right elbow of the tested object is larger than 91 and the abscissa of the right end point is larger than 221, the elbow back-and-forth swing amplitude of the wrong running position is judged to be too large.
C. If the left and right elbow motion trace of the tested object is between the points b (0, 91) and e (221, 0), the elbow swing back and forth amplitude determined as the wrong running position is too small.
D. If the ordinate of the left end point of the motion trail diagram of the left elbow and the right elbow of the tested object is larger than 91 and the abscissa of the right end point is smaller than 221, the elbow with the wrong running posture is judged to swing forwards too small and swing backwards too large.
E. If the ordinate of the left end point of the motion trail diagram of the left elbow and the right elbow of the tested object is less than 91 and the abscissa of the right end point is more than 221, the elbow with the wrong running posture is judged to swing too far forward and too little backward.
F. If the motion trace graphs of the left and right elbows of the tested person are not consistent, the swing of the left and right elbows is judged to be asymmetric due to wrong running posture.
If the judgment result is A, the result can be directly stored, and the tested object can be downloaded from the intelligent terminal.
And if the judgment result is not A, entering a back-end processing module for further operation. If the result is B, the standard degree of the running posture of the tested person is
If the result is C, the standard degree of the running posture of the tested person is
If the result is D, the standard degree of the running posture of the tested person is
If the result is E, the standard degree of the running posture of the tested person is
And finally, storing the data for the testee to download from the intelligent terminal.
As shown in fig. 3, the present invention further provides a human running posture recognition apparatus based on computer vision according to the human running posture recognition and analysis method based on computer vision, which is used for implementing the human running posture recognition method based on computer vision, and specifically includes the following steps:
the running machine and the camera are used for shooting standard running postures and various typical wrong running postures on the running machine in the first step of the human body running posture identification and analysis method based on computer vision, and shooting a test object in the fourth step;
the cloud computing module is used for drawing a running posture curve graph in the first step of the human body posture running posture identification and analysis method based on computer vision, carrying out convolutional neural network training on various typical wrong running postures and standard running postures in the fourth step to obtain a posture identification model, identifying the running posture type of a tested object in the fourth step, carrying out contrast operation on the tested object in the fifth step, and outputting a posture standard degree score and a correction suggestion;
and the back-end processing module is used for storing the posture standard degree score and the correction opinion obtained in the fifth step of the human body running posture identification and analysis method based on computer vision.
And the intelligent terminal is used for downloading the posture standard degree score and the correction opinion from the back-end processing module.
The invention is not to be considered as limited to the particular embodiments shown and described, but is to be understood that various modifications, equivalents, improvements and the like can be made without departing from the spirit and scope of the invention.
Claims (7)
1. The human body running posture identification and analysis method based on computer vision comprises the following steps:
acquiring data, shooting various typical wrong running postures and standard running postures on a running machine, and drawing a running posture movement track graph of the shot object with the height of 170 cm;
step two, data classification, namely performing posture classification on the running posture motion trail diagram obtained in the step one;
step three, data training, namely, performing recognition training on the pictures subjected to posture classification in the step two by adopting a convolutional neural network method, performing grouping training on the motion trail pictures according to standard running postures and various typical error running postures to obtain a running posture recognition model group corresponding to the standard running postures and obtain a posture recognition model;
step four, gesture recognition, namely shooting the running gesture of the test object, searching and recognizing the running gesture movement locus diagram of the test object in the real-time video through the gesture recognition model obtained in the step three, and confirming the user gesture which is consistent with the gesture classification in the gesture recognition model;
and step five, evaluating and analyzing the posture, comparing the user posture identified in the step four with a standard posture motion trail diagram through a posture identification model, and outputting a posture standard degree score and a correction opinion.
2. The human running gesture recognition analysis method based on computer vision as claimed in claim 1, wherein the data collection comprises gesture shooting, video uploading, video preprocessing and drawing of motion trail graph;
the speed of the treadmill is a fixed value when the posture is shot;
the data acquisition is used for shooting standard posture runners and various typical non-standard posture runners at a plurality of specified angles;
uploading a running video shot in real time to video processing software;
video preprocessing, including dryness removal, video segmentation, key frame extraction and feature extraction;
drawing a motion trail graph, and drawing a running posture motion trail graph according to the motion trail of the mark points of each part of the body of the tested object in the video;
and when the motion trail graph is drawn, scaling the running posture motion trail graph into a running posture motion trail graph with the specified height of 170cm according to the height of the tested object in the video.
3. The method for human body running posture recognition and analysis based on computer vision as claimed in claim 1, wherein the body parts of the user, such as head, shoulder, hand, upper arm, lower arm, elbow, torso, hip, etc., are marked and photographed at the time of data collection.
4. The human body running posture recognition and analysis method based on computer vision as claimed in claim 1, characterized in that the posture classification in the second step is to classify the data into standard running posture and non-standard running posture; the nonstandard running postures are divided into the conditions that the left-right and up-down swinging amplitudes of the head, the trunk and the hip are too large, and the front-back, left-right and up-down swinging amplitudes of the shoulder, the hand, the upper arm, the lower arm and the elbow are too large and the left-right and left-right are asymmetric.
5. The human body running posture recognition and analysis method based on computer vision as claimed in claim 1, characterized in that the step four posture recognition is performed to each calibration part of the body of the tested object according to a running posture recognition model.
6. The human running posture identifying and analyzing method based on computer vision as claimed in claim 1, wherein the five-step posture evaluation analysis is performed by setting grades with different deviation degrees according to a standard running posture motion trail diagram, and outputting a standard grade and a correction opinion through a comparison operation of the tested object running posture motion trail diagram and the standard running posture motion trail diagram.
7. Human body running posture recognition and analysis device based on computer vision is characterized in that:
the system comprises a treadmill and a camera, and is used for shooting a test object on the treadmill;
the cloud computing module is used for drawing a running posture motion trail diagram, carrying out convolutional neural network training on typical error running postures and standard running postures to obtain a posture recognition model, identifying the running posture type of the tested object, carrying out comparison operation on the tested object, and outputting a posture standard degree score and a correction suggestion;
the back-end processing module is used for storing the posture standard degree score and the correction suggestion obtained by the human body running posture recognition analysis method based on computer vision;
and the intelligent terminal is used for downloading the posture standard degree score and the correction opinion from the back-end processing module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910985432.5A CN111259716A (en) | 2019-10-17 | 2019-10-17 | Human body running posture identification and analysis method and device based on computer vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910985432.5A CN111259716A (en) | 2019-10-17 | 2019-10-17 | Human body running posture identification and analysis method and device based on computer vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111259716A true CN111259716A (en) | 2020-06-09 |
Family
ID=70948431
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910985432.5A Pending CN111259716A (en) | 2019-10-17 | 2019-10-17 | Human body running posture identification and analysis method and device based on computer vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111259716A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111757254A (en) * | 2020-06-16 | 2020-10-09 | 北京软通智慧城市科技有限公司 | Skating motion analysis method, device and system and storage medium |
| CN112001566A (en) * | 2020-09-11 | 2020-11-27 | 成都拟合未来科技有限公司 | Optimization method, device, equipment and medium of fitness training model |
| CN113009960A (en) * | 2021-02-03 | 2021-06-22 | 上海橙捷健康科技有限公司 | Time synchronization method for camera image data and pressure treadmill data |
| CN113485669A (en) * | 2021-06-23 | 2021-10-08 | 深圳市加糖电子科技有限公司 | Music adjustment system based on motion step frequency |
| CN113892928A (en) * | 2021-10-14 | 2022-01-07 | 首都体育学院 | Body-building behavior monitoring system based on Beidou positioning and narrowband Internet of things |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102368297A (en) * | 2011-09-14 | 2012-03-07 | 北京英福生科技有限公司 | Equipment, system and method for recognizing actions of detected object |
| CN103596626A (en) * | 2012-02-29 | 2014-02-19 | 美津浓株式会社 | Running form diagnostic system and method for scoring running form |
| WO2017025979A1 (en) * | 2015-08-10 | 2017-02-16 | Kumar Singh Anshuman | System and method for identifying posture details and evaluating athletes' performance |
| 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 |
| CN106618529A (en) * | 2016-12-07 | 2017-05-10 | 安徽新华传媒股份有限公司 | Intelligent running exercise breakdown action teaching system based on precise posture detection |
| CN107174255A (en) * | 2017-06-15 | 2017-09-19 | 西安交通大学 | Three-dimensional gait information gathering and analysis method based on Kinect somatosensory technology |
| CN107909060A (en) * | 2017-12-05 | 2018-04-13 | 前海健匠智能科技（深圳）有限公司 | Gymnasium body-building action identification method and device based on deep learning |
| CN109692003A (en) * | 2017-10-20 | 2019-04-30 | 深圳市鹰硕技术有限公司 | A kind of children's running posture correction training system |
-
2019
- 2019-10-17 CN CN201910985432.5A patent/CN111259716A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102368297A (en) * | 2011-09-14 | 2012-03-07 | 北京英福生科技有限公司 | Equipment, system and method for recognizing actions of detected object |
| CN103596626A (en) * | 2012-02-29 | 2014-02-19 | 美津浓株式会社 | Running form diagnostic system and method for scoring running form |
| WO2017025979A1 (en) * | 2015-08-10 | 2017-02-16 | Kumar Singh Anshuman | System and method for identifying posture details and evaluating athletes' performance |
| 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 |
| CN106618529A (en) * | 2016-12-07 | 2017-05-10 | 安徽新华传媒股份有限公司 | Intelligent running exercise breakdown action teaching system based on precise posture detection |
| CN107174255A (en) * | 2017-06-15 | 2017-09-19 | 西安交通大学 | Three-dimensional gait information gathering and analysis method based on Kinect somatosensory technology |
| CN109692003A (en) * | 2017-10-20 | 2019-04-30 | 深圳市鹰硕技术有限公司 | A kind of children's running posture correction training system |
| CN107909060A (en) * | 2017-12-05 | 2018-04-13 | 前海健匠智能科技（深圳）有限公司 | Gymnasium body-building action identification method and device based on deep learning |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111757254A (en) * | 2020-06-16 | 2020-10-09 | 北京软通智慧城市科技有限公司 | Skating motion analysis method, device and system and storage medium |
| CN111757254B (en) * | 2020-06-16 | 2022-09-13 | 北京软通智慧科技有限公司 | Skating motion analysis method, device and system and storage medium |
| CN112001566A (en) * | 2020-09-11 | 2020-11-27 | 成都拟合未来科技有限公司 | Optimization method, device, equipment and medium of fitness training model |
| CN112001566B (en) * | 2020-09-11 | 2024-04-30 | 成都拟合未来科技有限公司 | Optimization method, device, equipment and medium of fitness training model |
| CN113009960A (en) * | 2021-02-03 | 2021-06-22 | 上海橙捷健康科技有限公司 | Time synchronization method for camera image data and pressure treadmill data |
| CN113485669A (en) * | 2021-06-23 | 2021-10-08 | 深圳市加糖电子科技有限公司 | Music adjustment system based on motion step frequency |
| CN113892928A (en) * | 2021-10-14 | 2022-01-07 | 首都体育学院 | Body-building behavior monitoring system based on Beidou positioning and narrowband Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111259716A (en) | Human body running posture identification and analysis method and device based on computer vision | |
| CN108564596B (en) | Intelligent comparison analysis system and method for golf swing video | |
| US20210228959A1 (en) | Kinect-based auxiliary training system for basic badminton movements | |
| CN111444890A (en) | Sports data analysis system and method based on machine learning | |
| CN113627409B (en) | Body-building action recognition monitoring method and system | |
| CN112422946A (en) | Intelligent yoga action guidance system based on 3D reconstruction | |
| CN115624735B (en) | Auxiliary training system for ball games and working method | |
| CN110227243A (en) | Table tennis practice intelligent correcting system and its working method | |
| CN111709365A (en) | Automatic human motion posture detection method based on convolutional neural network | |
| CN115188078A (en) | Ping-pong intelligent action training method based on voice interaction and attitude estimation | |
| CN114618142A (en) | Auxiliary training system and method for table tennis sports | |
| CN110929595A (en) | System and method for training or entertainment with or without ball based on artificial intelligence | |
| CN114005180A (en) | Motion scoring method and device for badminton | |
| CN116758459A (en) | Real-time analysis system and method for badminton match | |
| CN116246347A (en) | Standard judging method and scoring device for basic motor skills of human body | |
| CN115346273A (en) | Snow sport information monitoring method and related device | |
| Zhang | Construction of sports recognition system based on sports visual image technology under the background of information technology | |
| CN112364815A (en) | High jump posture detection method for high jump athletes based on three-dimensional model | |
| CN112784699A (en) | Method and system for realizing posture evaluation guidance of sports coach | |
| Tomas et al. | Comparative Study on Model Skill of ERT and LSTM in Classifying Proper or Improper Execution of Free Throw, Jump Shot, and Layup Basketball Maneuvers | |
| Meng | Deep Learning Algorithm and Video Image Processing-based Basketball Training System | |
| Chen et al. | Research on Table Tennis Swing Recognition Based on Lightweight OpenPose | |
| CN117315780B (en) | Badminton racket swinging motion recognition and three-dimensional track reconstruction method and system | |
| CN108009504A (en) | A kind of recognition methods of moving sphere, device and storage medium | |
| CN114241603B (en) | Shuttlecock action recognition and level grade evaluation method and system based on wearable equipment |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200609 |
|
| WD01 | Invention patent application deemed withdrawn after publication |