CN111111111A - Real-time fitness monitoring system and method - Google Patents
Real-time fitness monitoring system and method Download PDFInfo
- Publication number
- CN111111111A CN111111111A CN202010037410.9A CN202010037410A CN111111111A CN 111111111 A CN111111111 A CN 111111111A CN 202010037410 A CN202010037410 A CN 202010037410A CN 111111111 A CN111111111 A CN 111111111A
- Authority
- CN
- China
- Prior art keywords
- real
- time
- thermal imaging
- user
- character model
- 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
- A63B24/00—Electric or electronic controls for exercising apparatus of preceding groups; Controlling or monitoring of exercises, sportive games, training or athletic performances
- A63B24/0003—Analysing the course of a movement or motion sequences during an exercise or trainings sequence, e.g. swing for golf or tennis
- A63B24/0006—Computerised comparison for qualitative assessment of motion sequences or the course of a movement
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B24/00—Electric or electronic controls for exercising apparatus of preceding groups; Controlling or monitoring of exercises, sportive games, training or athletic performances
- A63B24/0062—Monitoring athletic performances, e.g. for determining the work of a user on an exercise apparatus, the completed jogging or cycling distance
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B24/00—Electric or electronic controls for exercising apparatus of preceding groups; Controlling or monitoring of exercises, sportive games, training or athletic performances
- A63B24/0087—Electric or electronic controls for exercising apparatus of groups A63B21/00 - A63B23/00, e.g. controlling load
-
- 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
- A63B71/06—Indicating or scoring devices for games or players, or for other sports activities
- A63B71/0619—Displays, user interfaces and indicating devices, specially adapted for sport equipment, e.g. display mounted on treadmills
- A63B71/0622—Visual, audio or audio-visual systems for entertaining, instructing or motivating the user
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B24/00—Electric or electronic controls for exercising apparatus of preceding groups; Controlling or monitoring of exercises, sportive games, training or athletic performances
- A63B24/0003—Analysing the course of a movement or motion sequences during an exercise or trainings sequence, e.g. swing for golf or tennis
- A63B24/0006—Computerised comparison for qualitative assessment of motion sequences or the course of a movement
- A63B2024/0012—Comparing movements or motion sequences with a registered reference
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B24/00—Electric or electronic controls for exercising apparatus of preceding groups; Controlling or monitoring of exercises, sportive games, training or athletic performances
- A63B24/0062—Monitoring athletic performances, e.g. for determining the work of a user on an exercise apparatus, the completed jogging or cycling distance
- A63B2024/0065—Evaluating the fitness, e.g. fitness level or fitness index
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B24/00—Electric or electronic controls for exercising apparatus of preceding groups; Controlling or monitoring of exercises, sportive games, training or athletic performances
- A63B24/0087—Electric or electronic controls for exercising apparatus of groups A63B21/00 - A63B23/00, e.g. controlling load
- A63B2024/009—Electric or electronic controls for exercising apparatus of groups A63B21/00 - A63B23/00, e.g. controlling load the load of the exercise apparatus being controlled in synchronism with visualising systems, e.g. hill slope
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B24/00—Electric or electronic controls for exercising apparatus of preceding groups; Controlling or monitoring of exercises, sportive games, training or athletic performances
- A63B24/0087—Electric or electronic controls for exercising apparatus of groups A63B21/00 - A63B23/00, e.g. controlling load
- A63B2024/0093—Electric or electronic controls for exercising apparatus of groups A63B21/00 - A63B23/00, e.g. controlling load the load of the exercise apparatus being controlled by performance parameters, e.g. distance or speed
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B24/00—Electric or electronic controls for exercising apparatus of preceding groups; Controlling or monitoring of exercises, sportive games, training or athletic performances
- A63B24/0087—Electric or electronic controls for exercising apparatus of groups A63B21/00 - A63B23/00, e.g. controlling load
- A63B2024/0096—Electric or electronic controls for exercising apparatus of groups A63B21/00 - A63B23/00, e.g. controlling load using performance related parameters for controlling electronic or video games or avatars
-
- 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
- A63B71/06—Indicating or scoring devices for games or players, or for other sports activities
- A63B71/0619—Displays, user interfaces and indicating devices, specially adapted for sport equipment, e.g. display mounted on treadmills
- A63B71/0622—Visual, audio or audio-visual systems for entertaining, instructing or motivating the user
- A63B2071/0636—3D visualisation
-
- 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
- A63B71/06—Indicating or scoring devices for games or players, or for other sports activities
- A63B71/0619—Displays, user interfaces and indicating devices, specially adapted for sport equipment, e.g. display mounted on treadmills
- A63B2071/0647—Visualisation of executed movements
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2220/00—Measuring of physical parameters relating to sporting activity
- A63B2220/80—Special sensors, transducers or devices therefor
- A63B2220/803—Motion sensors
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2220/00—Measuring of physical parameters relating to sporting activity
- A63B2220/80—Special sensors, transducers or devices therefor
- A63B2220/806—Video cameras
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2230/00—Measuring physiological parameters of the user
- A63B2230/04—Measuring physiological parameters of the user heartbeat characteristics, e.g. ECG, blood pressure modulations
- A63B2230/06—Measuring physiological parameters of the user heartbeat characteristics, e.g. ECG, blood pressure modulations heartbeat rate only
- A63B2230/062—Measuring physiological parameters of the user heartbeat characteristics, e.g. ECG, blood pressure modulations heartbeat rate only used as a control parameter for the apparatus
-
- 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
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Physical Education & Sports Medicine (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a real-time fitness monitoring system and a real-time fitness monitoring method, wherein the real-time fitness monitoring system comprises a far infrared thermal imaging heart rate detection module, a camera image video acquisition module, a display module, a data transmission module, a master control system and a cloud server; the far infrared thermal imaging heart rate detection module comprises a far infrared thermal imager assembly and a temperature measurement assembly, and the camera image video acquisition module comprises a multi-camera assembly and an image filtering assembly; the data transmission module transmits data information to a master control system; after the main control system is preprocessed, data information is sent to a cloud server, the cloud server generates a standard 3D character model and a real-time 3D character model according to the data information, and the standard 3D character model and the real-time 3D character model are displayed on a display module through the main control system. The real-time body-building monitoring system can not only facilitate users to correct wrong body-building actions, but also know the fatigue degree of body muscles in real time and avoid damage.
Description
Technical Field
The invention relates to a fitness monitoring system, in particular to a fitness real-time monitoring system and method.
Background
With the coming of the comprehensive well-being times, the living standard of people is continuously improved, and the personal health is more and more valued; many people can select fitness equipment to perform fitness in vacant time periods, so that the physical quality of the national people in China is improved; however, most people often have no special fitness coach for guidance during the fitness process, and the fitness users cannot know how to exercise the fitness effect, even sometimes the fitness effect is opposite because of improper training method.
In the existing fitness system, a fitness monitoring system capable of monitoring the fitness state of the user in real time appears, for example, the invention patent with the publication number of CN107551525B discloses an auxiliary fitness system and method, and a fitness apparatus, wherein the auxiliary fitness system comprises: the thermal imaging device is used for receiving an infrared signal from a human body and generating a human body image by performing thermal imaging processing on the basis of the infrared signal; the comparison device is used for comparing the human body image with a reference image of a standard fitness action to generate a comparison result; and the display device is used for displaying the human body image and the comparison result of the human body image and the reference image. Through the auxiliary fitness system, a fitness person can observe whether the action of the fitness person is standard or not through a comparison result displayed by the display device, and can also observe the movement state of muscles, so that physical damage caused by action errors or excessive movement is avoided. The assisted exercise system, however, is still unable to more intuitively demonstrate its exercise effect to the user.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a real-time fitness monitoring system, which can more intuitively show the fitness effect of a user, can conveniently correct wrong fitness actions of the user in time, and can also provide the user with real-time understanding of the fatigue degree of body muscles so as to have a rest in time and avoid damage.
Another object of the present invention is to provide a real-time fitness monitoring method.
The technical scheme for solving the technical problems is as follows:
a real-time monitoring system for body-building comprises a far-infrared thermal imaging heart rate detection module, a camera image video acquisition module, a display module, a data transmission module, a master control system and a cloud server, wherein,
the far infrared thermal imaging heart rate detection module is used for acquiring a thermal imaging image of a user corresponding to a training area, and comprises a far infrared thermal imager assembly and a temperature measurement assembly, wherein the far infrared thermal imager assembly is used for acquiring a muscle thermal imaging image and a face thermal imaging image of the user corresponding to the training area; the temperature measurement assembly is used for acquiring temperature data of the body surface of a user;
the camera image video acquisition module is used for acquiring video image information of a fitness posture of a user and comprises a multi-camera component and an image filtering component, wherein the multi-camera component is used for acquiring posture information of the user during fitness in real time; the image filtering component is used for reducing noise generated by working environment and hardware condition in image video information collected by the multi-camera component;
the data transmission module is used for transmitting image data of the far infrared thermal imager assembly, user body surface temperature data acquired by the temperature measurement assembly and image video information of the multi-camera assembly to the master control system;
the main control system preprocesses the received data information, and sends the data information to the cloud server through the wireless transmission module, and the cloud server is used for processing and storing the data information, generating a standard 3D character model with standard actions and a real-time 3D character model consistent with the current body-building actions of the user, and displaying the standard 3D character model and the real-time 3D character model on the display module through the main control system.
Preferably, the multi-camera assembly comprises three cameras, the three cameras use the fitness equipment as an origin and are annularly distributed around the fitness equipment, and an included angle between every two adjacent cameras is 120 degrees.
Preferably, the far infrared thermal imager of the far infrared thermal imager assembly is placed right in front of the user.
Preferably, the display module is a display or AR glasses.
A real-time fitness monitoring method comprises the following steps:
(1) when a user moves on the body builder, a far infrared thermal imaging instrument component in the far infrared thermal imaging heart rate detection module collects image data of a training area corresponding to the user, wherein the image data comprises a muscle thermal imaging graph and a face thermal imaging graph; the temperature measurement assembly collects temperature data of the body surface of a user; meanwhile, the camera image video acquisition module acquires video image information of the body-building action of the user;
(2) the data transmission module transmits the image data acquired by the far infrared thermal imager assembly, the body surface temperature data of the user acquired by the temperature measurement assembly and the video image information acquired by the camera image video acquisition module to the master control system;
(3) after receiving the data information, the master control system preprocesses the data information and transmits the data information to the cloud server;
(4) after the cloud server receives the data information, processing the collected video image information to generate two 3D character models, wherein one 3D character model is consistent with the real-time body-building action of the user and is a real-time 3D character model; the other 3D character model is consistent with the real-time body-building action of the user and is a correct body-building action and is a standard 3D character model; then analyzing and comparing the difference of each part of the action of the real-time 3D character model and the standard 3D character model corresponding to the real-time 3D character model, and feeding back the comparison result to the master control system;
(5) the cloud server processes the image data acquired by the far-infrared thermal imaging heart rate detection module, calculates the fatigue degree of muscles of the user, and feeds the fatigue degree of the muscles back to the master control system;
(6) the main control system displays the real-time 3D character model and the standard 3D character model corresponding to the real-time 3D character model on the display module at the same time, and marks the parts of the user with irregular and standard body-building actions on the real-time 3D character model by different colors respectively; meanwhile, the master control system displays the fatigue degree of the muscles of the user on the real-time 3D character model in a color superposition mode;
(7) the user monitors the body building action of the user in real time through the display module, corrects wrong body building action in time, and decides whether to have a rest or not by monitoring the fatigue degree of muscles on the 3D character model.
Preferably, in the step (4), the method for constructing a 3D character model includes the steps of:
(4-1) after receiving the video image information transmitted by the master control system, the cloud server screens out the standard fitness actions of each stage of each fitness project and generates a standard 3D character model database which can be referred by a user and has the standard fitness actions of each fitness project;
(4-2) after the standard 3D character model database is constructed, the cloud server matches a corresponding standard 3D character model of the fitness item in a pre-established standard 3D character model database which stores the correct fitness action of each fitness item through processing and calculation according to the video image information of the current fitness action of the user; meanwhile, the cloud server generates a current real-time 3D character model of the user after processing video image information of the current body-building action of the user.
Preferably, in step (1), the cloud server obtains the heart rate of the user through a thermal imaging-based non-contact heart rate detection method, and feeds the heart rate back to the display module in real time, where the thermal imaging-based non-contact heart rate detection method includes the following steps:
(1-1) converting the thermal imaging graph into a gray-scale graph by using an image processing technology, binarizing the converted gray-scale graph, and then primarily processing the binarized gray-scale graph by using a corrosion algorithm and an expansion algorithm;
(1-2) selecting a reserved human face and a naked neck region in the processed gray-scale image, and setting a lower 1/3 region of the face in the thermal imaging image as a region of interest to be tracked; obtaining the outline of a human body by using the boundary points of the minimum unit circle circumscribed picture, calculating and obtaining the range of the human face and the naked neck region and reserving the range;
(1-3) removing noise by using a wavelet denoising algorithm;
(1-4) processing the corresponding numerical value of the region of interest, and calculating the heart rate R of the user per minute, wherein the calculation formula is as follows:
R＝q×f×60/t
wherein t represents the current frame number, q represents the peak number of the signal after wavelet packet reconstruction, and f represents the sampling frequency of the video.
Preferably, in step (5), the analyzing of the fatigue degree of the muscle of the user includes the steps of:
(5-1) the far infrared thermal imaging heart rate detection module collects a local body thermal imaging image of the fitness part of the user during movement and sends the local body thermal imaging image to the master control system;
(5-2) preprocessing the local body thermal imaging graph by the master control system, cutting the local thermal imaging graph of each heating area in the body-building part corresponding to the user, and sending the local thermal imaging graph to the cloud server;
(5-3) the cloud server inputs the local thermal imaging graph into a pre-trained first convolution neural network model, and a thermal imaging graph with heating of triceps is found in the multiple thermal imaging graphs through the first convolution neural network model;
(5-4) inputting the thermal imaging graph with the heating of the triceps into a second convolutional neural network model trained in advance, comparing the thermal imaging graph with the heating of the triceps when the user performs the fitness item with the thermal imaging graph with the heating of the triceps when the user performs the fitness item under the complete standard action through the second convolutional neural network model, and obtaining the matching degree of the thermal imaging graph and the thermal imaging graph;
(5-5) the cloud server further processes the triceps thermal imaging image output from the first convolution neural network model to obtain a temperature value of the image, and calibrates the temperature values obtained at all time points on the same coordinate axis to obtain a curve relating to temperature and time; the fatigue degree of the muscle is indirectly judged through the gradient value and the track of the curve, and a corresponding body-building scheme and a health safety prompt are obtained;
(5-6), superimposing the relevant body part of the exercise aimed at by the fitness equipment on the real-time 3D character model in a pattern mode; displaying the real-time 3D character model in a color superposition mode according to the matching degree correlation result; if the matching degree is higher than a preset value, displaying green in a relevant area in the real-time 3D character model, and if the matching degree is lower than the preset value, displaying red in the relevant area in the real-time 3D character model;
and (5-7) the master control system controls the display module to play the corresponding fitness scheme and fitness safety prompt, and displays the real-time 3D human body model in the display module.
Preferably, in step (5-3), the training method of the first convolutional neural network model includes: the thermal imaging images of a large number of users after body building actions are collected respectively, the thermal imaging images of the triceps which generate heat when corresponding fitness equipment is cut out from the collected thermal imaging images are used as a training set, and the training set is subjected to learning training by using a neural network.
Preferably, in step (5-4), the training method of the second convolutional neural network model includes: a large number of thermal imaging pictures of a human body after the body-building action is carried out under the complete standard action are respectively collected, thermal imaging pictures of triceps heating are cut out in the thermal imaging pictures, the thermal imaging pictures are used as a training set, and a neural network is used for learning and training the training set.
Compared with the prior art, the invention has the following beneficial effects:
1. the real-time body-building monitoring system acquires video image information of body-building actions of a user through the camera image video acquisition module; the real-time 3D character model and the standard 3D character model are generated by the cloud server according to the received video image information, and the parts of the user with irregular and standard body-building actions are displayed in the display module in different colors on the real-time 3D character model by comparing the real-time 3D character model with the standard 3D character model. Therefore, the user can compare and reference the data in real time so as to correct the data in time, thereby improving the body-building effect.
2. The body-building real-time monitoring system acquires image data and temperature data of a training area corresponding to a user through a far infrared thermal imaging heart rate detection module; calculating the fatigue degree of muscles of the user according to the received image data and the temperature data, and displaying the fatigue degree of the muscles on the real-time 3D character model in a color superposition mode; and displays it in the display module. Therefore, the user can know whether the body-building action is wrong or not in the display module, and can also know the fatigue strength of muscles in the body-building area of the user so as to decide whether to rest or not and avoid injury.
3. The real-time body-building monitoring system can more intuitively show the body-building effect of the user, not only can facilitate the user to correct wrong body-building actions in time, but also can provide the user to know the fatigue degree of body muscles in real time so as to have a rest in time, thereby avoiding damage.
4. The body-building real-time monitoring system acquires the thermal imaging graph of the corresponding area when the user trains through the far infrared thermal imaging heart rate detection module, and the muscle movement condition of the user can be obtained in the thermal imaging graph, so that the muscle movement condition of the corresponding training area when the user trains can be displayed to the user more accurately, and the situation that the user exercises correctly but the internal muscles of the user exert incorrect force during body building is prevented.
Drawings
Fig. 1 is a block flow diagram of an embodiment of the real-time fitness monitoring system of the present invention.
Fig. 2 is a block diagram of the far infrared thermal imaging heart rate detection module.
Fig. 3 is a block diagram of the structure of the camera image video capture module.
Fig. 4 is a diagram of the positional relationship between the multi-camera assembly and the exercise machine.
Fig. 5 is a schematic flow chart of the real-time fitness monitoring method of the present invention.
Fig. 6 is a schematic flow chart of the non-contact heart rate detection method based on thermal imaging.
FIG. 7 is a flowchart illustrating a method for constructing a 3D character model.
Fig. 8 is a flowchart illustrating a user muscle fatigue level analysis.
Detailed Description
The present invention will be described in further detail with reference to examples and drawings, but the present invention is not limited thereto.
Referring to fig. 1-4, the real-time body-building monitoring system of the present invention comprises a far-infrared thermal imaging heart rate detection module 1, a camera image video acquisition module 2, a display module 7, a data transmission module 3, a general control system 4 and a cloud server 6, wherein,
the far infrared thermal imaging heart rate detection module 1 is used for collecting a muscle thermal imaging graph and a face thermal imaging graph of a training area corresponding to a user, and comprises a far infrared thermal imaging instrument assembly 1-1 and a temperature measurement assembly 1-2, wherein the far infrared thermal imaging instrument assembly 1-1 is used for collecting the muscle thermal imaging graph and the face thermal imaging graph of the training area corresponding to the user; the temperature measurement component 1-2 is used for collecting temperature data of the body surface of a user, and specifically can adopt an infrared thermometer;
the camera image video acquisition module 2 is used for acquiring video image information of the posture of a user, and comprises a multi-camera component 2-1 and an image filtering component 2-2, wherein the multi-camera component 2-1 is used for acquiring the posture information of the user during body building in real time, and a depth camera can be particularly adopted; the image filtering component 2-2 is used for reducing noise generated by working environment and hardware condition in the image video data collected by the multi-camera component 2-1, and a DSP integrated circuit can be specifically adopted;
the data transmission module 3 is used for transmitting the image data of the far infrared thermal imager assembly 1-1, the user body surface temperature data acquired by the temperature measurement assembly 1-2 and the image video data of the multi-camera assembly 2-1 to the master control system 4;
the main control system 4 preprocesses the received data information and then sends the data information to the cloud server 6 through the wireless transmission module 5 (such as WiFi), the cloud server 6 is used for processing and storing the data information, a standard 3D character model with standard actions and a real-time 3D character model consistent with the current body-building actions of the user are generated, and the data information is displayed on the display module through the main control system 4.
The data processing of the cloud server 6 includes the following processes:
firstly, converting a thermal imaging image into a gray image, and performing morphological operation on the gray image to smooth the boundary of the gray image and eliminate tiny noise points; since there may be several regions with the highest local temperature in the thermography image, which may have an effect on the result, it is necessary to further determine which regions belong to the regions where the pectoral muscles are exercised;
then, calibrating a plurality of possible muscle exercise areas in the thermal imaging image, dividing the images of the calibration areas, normalizing the images of the calibration areas to make the sizes of the images uniform to be NxN, and predicting the calibrated areas by using a pre-trained first convolution neural network model; judging the muscle area currently exercising according to the prediction result; segmenting the image of the muscle area exercised by the user at present, and carrying out normalization processing to make the size of the image uniform to be NxN; and then predicting the muscle image by using a pre-trained second convolutional neural network model, and judging whether the region is a correct muscle exercise region according to a prediction output result.
Subsequently, according to the face thermal imaging image, image preprocessing is carried out on the face thermal imaging image, including image binarization, morphological operation, Gaussian filtering and the like, a face area is calibrated, a TLD algorithm is used for tracking the face area in a motion state, and the area is an area of interest; and carrying out gray processing on the region of interest, and calculating a heart rate value according to the frequency change of the gray value at a certain time.
Then, according to the video image information of the fitness posture of the user, the video image information is processed and calculated through the cloud server 6 and matched with the standard 3D character model in the created standard 3D character model database, and therefore the real-time 3D character model which is the same as the fitness posture of the user at present is generated.
In addition, because the far infrared thermal imaging heart rate detection module is used for collecting the thermal imaging image of the corresponding area when the user trains, the situation of muscle movement of the user can be obtained in the thermal imaging image, so that the movement situation of the muscle of the corresponding training area when the user exercises can be displayed to the user more accurately, and the situation that the internal muscle strength is incorrect although the posture of the user is correct during the exercise is prevented, for example, when a user takes a sit-up, the posture of the user is correct, but the force exerting mode is incorrect, for example, the waist strength is adopted instead of the abdominal strength, and the exercise effect can be influenced. Therefore, the thermal imaging picture of the corresponding region is acquired by the far infrared thermal imaging heart rate detection module during the training of the user, the user can clearly see the exercise condition of the muscles of the abdomen of the user on the display module 7, and the fatigue degree of the abdomen of the user is analyzed in combination, so that whether the muscle strength is correct or not is known, and the fitness effect is improved.
Finally, the overall control system 4 matches the analyzed data result with the information of the preset database, and displays the matching result on the display module 7, for example, on the AR glasses. And according to the generated standard 3D character model and the real-time 3D character model, overlapping the standard 3D character model and the real-time 3D character model through AR glasses and displaying the real-time 3D character model in the real world. The corresponding positions of the current exercise areas of the user on the 3D character model are displayed in different colors, for example, the correct exercise area is displayed in green, the incorrect exercise area is displayed in red, and the user can intuitively know whether the current body building action is correct or not through the different colors.
In addition, according to the obtained heart rate value and the body temperature value, the main control system 4 matches the analysis results of the heart rate value and the body temperature value with the fitness scheme in the preset database, and displays the fitness scheme and the health safety prompt through AR glasses, so that the user can take exercises by referring to the fitness scheme and consider whether to have a rest according to the health safety prompt.
Referring to fig. 1-4, the multi-camera assembly 2-1 includes three cameras 2-11, the three cameras 2-11 are distributed around the exercise machine 8 in a ring shape with the exercise machine 8 as an origin, and an included angle between two adjacent cameras 2-11 is 120 °. Therefore, the body-building posture information of the user can be acquired in 360 degrees in an all-around manner.
Referring to fig. 1 to 4, the far infrared thermal imager of the far infrared thermal imager assembly 1-1 is placed right in front of a user. The purpose is in order to catch user pectoralis major muscle thermal imaging picture and face thermal imaging picture better, and the far infrared thermal imaging appearance is put to different positions according to different fitness equipment promptly.
The display module 7 in this embodiment is a display or AR glasses.
Referring to fig. 1-8, the real-time monitoring method for fitness of the invention comprises the following steps:
(1) when a user moves on the body builder, a far infrared thermal imaging heart rate detection module 1-1 in the far infrared thermal imaging heart rate detection module 1 collects image data of a training area corresponding to the user, wherein the image data comprises a muscle thermal imaging graph and a face thermal imaging graph; the temperature measurement component 1-2 collects temperature data of the body surface of a user; meanwhile, the camera image video acquisition module 2 acquires video image information of the body-building action of the user; the image filtering component 2-2 reduces the noise generated by the video image information collected by the camera component under the working environment and hardware conditions, thereby ensuring the accuracy of the collected image video data;
(2) the data transmission module 3 transmits the image data acquired by the far infrared thermal imager assembly 1-1, the body surface temperature data of the user acquired by the temperature measurement assembly 1-2 and the video image information acquired by the camera image video acquisition module 2 to the master control system 4;
(3) after receiving the data information, the master control system 4 pre-processes the data information, wherein different pre-processing technologies can be flexibly selected in the pre-processing process according to different acquired data information; transmitting the preprocessed data information to the cloud server 6;
(4) after receiving the data information, the cloud server 6 performs data processing on the data information, and generates two 3D character models by processing the collected video image information, wherein one 3D character model is consistent with the real-time body-building action of the user and is a real-time 3D character model; the other 3D character model is consistent with the real-time body-building action of the user and is in a correct body-building posture and is a standard 3D character model; meanwhile, the fatigue degree of the muscles of the user is calculated by processing the image data acquired by the far infrared thermal imaging heart rate detection module 1, and the fatigue degree of the muscles is displayed on the 3D character model in a color superposition mode; for example, the correct body-building posture of the part of the real-time 3D character model that is consistent with the standard 3D character model is color a, and the fatigue degree of the muscle of the part is higher than the preset value, and the part with the fatigue strength higher than the preset value is displayed as color B, and the displayed color of the muscle of the part is a + B in the real-time 3D character model, so that the user can observe whether the body-building action is correct or not, and the fatigue degree of the muscle of the corresponding area can be observed, and the rest time can be arranged reasonably.
(5) The cloud server 6 feeds back the 3D character model consistent with the real-time body-building action of the user and the 3D character model with the correct body-building action to the master control system 4, and the master control system 4 displays the 3D character model and the 3D character model in the display module 7; meanwhile, the master control system 4 controls the display module 7 to play the corresponding fitness scheme and the prompt of fitness safety;
(6) the user monitors the body building action of the user in real time through the display module 7, corrects wrong body building action in time, and decides whether to have a rest or not by monitoring the fatigue degree of muscles on the 3D character model.
Referring to fig. 1 to 8, in step (4), the method for constructing the 3D character model includes the steps of:
(4-1) after receiving the video image information transmitted by the master control system 4, the cloud server 6 screens out the standard fitness actions of each stage of each fitness project and generates a standard 3D character model database which can be referred by a user and has the standard fitness actions of each fitness project;
(4-2) after the standard 3D character model database is constructed, the cloud server 6 matches a corresponding standard 3D character model of the fitness item in a pre-established standard 3D character model database which stores the correct fitness action of each fitness item through processing and calculation according to the video image information of the current fitness action of the user; meanwhile, the cloud server 6 generates a current real-time 3D character model of the user after processing video image information of the current body-building action of the user;
(4-3) the cloud server 6 analyzes and calculates the difference of each part of the action of the real-time 3D character model and the standard 3D character model corresponding to the real-time 3D character model, and feeds back the difference to the total control system 4;
(4-4), the total control system 4 displays the real-time 3D character model and the standard 3D character model corresponding to the real-time 3D character model on the display module 7 at the same time, and marks the parts of the user with irregular and standard body-building actions on the real-time 3D character model by different colors respectively. For example, the regular part of the user body-building action is represented by green, and the irregular part is marked by red.
Referring to fig. 1 to 8, in step (1), the cloud server 6 obtains heart rate information of a user through a thermal imaging-based non-contact heart rate detection method, and feeds the heart rate information back to the display module 7 in real time, where the thermal imaging-based non-contact heart rate detection method includes the following steps:
(1-1) converting the thermal imaging graph into a gray-scale graph by using an OpenCV technology, binarizing the converted gray-scale graph by using the OpenCV technology, and then primarily processing the binarized image by using a corrosion algorithm and an expansion algorithm; the key point of the expansion algorithm and the corrosion algorithm is the selection of structural elements, which generally mainly comprise rectangular structural elements, cross structural elements and elliptical structural elements. Because the expansion of the cross structural element is suitable for objects with irregular shapes and more sharp protrusions at the edges, the cross structural element is selected in the embodiment, so that the original outline shape of the object can be kept to the greatest extent.
(1-2) selecting a reserved human face and a naked neck region from the processed image, and setting a lower 1/3 region of the face in the thermal imaging image as an interested region to be tracked by using a Yolo (YouOnlyLookOnCE) algorithm; obtaining the outline of a human body by using the boundary points of the minimum unit circle circumscribed picture, calculating and obtaining the range of the human face and the naked neck region and reserving the range; because the artery blood vessels of the human body are mainly distributed in the triangular areas from the two sides of the mouth to the nasal root area, the heart rate data calculated by the area has higher accuracy than the heart rate data calculated by other areas of the face. The Yolo algorithm integrates the separate components of object detection into a single neural network, the Yolo network uses the features of the entire image to predict each bounding box, while it can also predict all bounding boxes of all classes in the entire image. Therefore, the yolo network can comprehensively infer and predict all targets of the whole image, and end-to-end training and real-time detection are realized, wherein the yolo detection system framework is divided into three steps: a. adjusting the size of the input image, b, and performing convolution neural network calculation on the image; c. the resulting detection is thresholded by the confidence of the model.
(1-3) removing noise by using a wavelet denoising algorithm; the wavelet denoising algorithm can well reserve useful signals while eliminating noise. The basic idea of wavelet threshold denoising in this embodiment is to select the generated wavelet coefficients after wavelet transform processing the signal by Mallat algorithm. Because the wavelet coefficient of the signal is larger after wavelet decomposition, the wavelet coefficient of the noise is smaller, and the wavelet coefficient of the noise is smaller than that of the signal. By selecting a proper threshold, the wavelet coefficient larger than the threshold is considered to be generated by a signal and should be reserved, the wavelet coefficient smaller than the threshold is considered to be generated by noise, and the wavelet coefficient is set to be zero, so that the purpose of denoising is achieved. In addition, the quality of the wavelet denoising effect is related to the selection of the wavelet basis function and the threshold value. Wavelet packet analysis can provide a more refined analysis method for signals, which divides frequency bands in multiple layers, further decomposes high-frequency parts which are not subdivided in multi-resolution analysis, and can adaptively select corresponding frequency bands according to the characteristics of analysis signals so as to match the frequency spectrums of the signals, thereby improving time-frequency resolution.
(1-4) processing the corresponding numerical value of the region of interest, and calculating the heart rate R of the user per minute, wherein the calculation formula is as follows:
R＝q×f×60/t
wherein t represents the current frame number, q represents the peak number of the signal after wavelet packet reconstruction, and f represents the sampling frequency of the video.
Referring to fig. 1 to 8, in step (3), the method for analyzing the fatigue degree includes the steps of:
(1) the far infrared thermal imaging heart rate detection module 1 collects a local body thermal imaging image of a body-building part of a user during movement, and sends the local body thermal imaging image to the master control system 4;
(2) the main control system 4 preprocesses the local body thermal imaging graph, cuts the local thermal imaging graph of each heating area in the body-building part corresponding to the user and sends the local thermal imaging graph to the cloud server 6;
(3) the cloud server 6 inputs the local thermal imaging graph into a pre-trained first convolution neural network model, and finds a thermal imaging graph with the heating of triceps muscle from a plurality of thermal imaging graphs through the first convolution neural network model; the first convolution neural network model is constructed by the following steps: respectively collecting a large number of thermal imaging pictures of a user after body-building action, cutting out the thermal imaging pictures of the triceps when the body-building apparatus is used as a training set from the collected thermal imaging pictures, and learning and training the training set by using a neural network;
(4) inputting the thermal imaging graph of the triceps heating into a second convolutional neural network model trained in advance, comparing the thermal imaging graph of the triceps heating when the user carries out the fitness item with the thermal imaging graph of the triceps heating when the user carries out the fitness item under the complete standard action through the second convolutional neural network model, and obtaining the matching degree of the thermal imaging graph and the thermal imaging graph; the second convolutional neural network model is constructed by the following steps: respectively collecting a large number of thermal imaging pictures of human body after the body-building action under the complete standard action, cutting out the thermal imaging pictures of triceps heating in the thermal imaging pictures, using the thermal imaging pictures as a training set, learning and training the training set by using a neural network to finally obtain a training model,
(5) the cloud server 6 further processes the triceps thermal imaging image output from the first convolution neural network model to obtain a temperature value of the image, and calibrates the temperature values obtained at various time points on the same coordinate axis to obtain a curve of temperature and time;
(7) and indirectly judging the fatigue degree of the muscle through the gradient value and the track of the curve, and obtaining a corresponding body-building scheme and a health safety prompt.
(8) Superimposing the relevant body part of the exercise aimed at by the fitness equipment on the real-time 3D character model in a pattern mode; displaying a fitness effect on the real-time 3D character model in a color superposition mode according to the matching degree correlation result; for example: if the matching degree is higher than a preset value, displaying green in a related area in the real-time 3D character model, and if the matching degree is lower than the preset value, displaying red in the related area in the real-time 3D character model; here, the color overlay may be performed with the locations of standard and non-standard fitness motions of the fitness motions in the real-time 3D character model.
Besides the color superposition mode, the mode of pattern and color superposition can be adopted to display on the real-time 3D character model.
The present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents and are included in the scope of the present invention.
Claims (10)
1. A real-time monitoring system for body-building comprises a far-infrared thermal imaging heart rate detection module, a camera image video acquisition module, a display module, a data transmission module, a master control system and a cloud server,
the far infrared thermal imaging heart rate detection module is used for acquiring a thermal imaging image of a user corresponding to a training area, and comprises a far infrared thermal imager assembly and a temperature measurement assembly, wherein the far infrared thermal imager assembly is used for acquiring a muscle thermal imaging image and a face thermal imaging image of the user corresponding to the training area; the temperature measurement assembly is used for acquiring temperature data of the body surface of a user;
the camera image video acquisition module is used for acquiring video image information of a fitness posture of a user and comprises a multi-camera component and an image filtering component, wherein the multi-camera component is used for acquiring posture information of the user during fitness in real time; the image filtering component is used for reducing noise generated by working environment and hardware condition in image video information collected by the multi-camera component;
the data transmission module is used for transmitting image data of the far infrared thermal imager assembly, user body surface temperature data acquired by the temperature measurement assembly and image video information of the multi-camera assembly to the master control system;
the main control system preprocesses the received data information, and sends the data information to the cloud server through the wireless transmission module, and the cloud server is used for processing and storing the data information, generating a standard 3D character model with standard actions and a real-time 3D character model consistent with the current body-building actions of the user, and displaying the standard 3D character model and the real-time 3D character model on the display module through the main control system.
2. The real-time fitness monitoring system of claim 1, wherein the multi-camera assembly comprises three cameras, the three cameras are distributed around the fitness equipment in a ring shape with the fitness equipment as an origin, and an included angle between every two adjacent cameras is 120 degrees.
3. The real-time fitness monitoring system of claim 1, wherein the far infrared thermal imager of the far infrared thermal imager assembly is placed directly in front of the user.
4. The real-time fitness monitoring system of claim 1, wherein the display module is a display or AR glasses.
5. A real-time fitness monitoring method using the real-time fitness monitoring system according to any one of claims 1 to 4, comprising the following steps:
(1) when a user moves on the body builder, a far infrared thermal imaging instrument component in the far infrared thermal imaging heart rate detection module collects image data of a training area corresponding to the user, wherein the image data comprises a muscle thermal imaging graph and a face thermal imaging graph; the temperature measurement assembly collects temperature data of the body surface of a user; meanwhile, the camera image video acquisition module acquires video image information of the body-building action of the user;
(2) the data transmission module transmits the image data acquired by the far infrared thermal imager assembly, the body surface temperature data of the user acquired by the temperature measurement assembly and the video image information acquired by the camera image video acquisition module to the master control system;
(3) after receiving the data information, the master control system preprocesses the data information and transmits the data information to the cloud server;
(4) after the cloud server receives the data information, processing the collected video image information to generate two 3D character models, wherein one 3D character model is consistent with the real-time body-building action of the user and is a real-time 3D character model; the other 3D character model is consistent with the real-time body-building action of the user and is a correct body-building action and is a standard 3D character model; then analyzing and comparing the difference of each part of the action of the real-time 3D character model and the standard 3D character model corresponding to the real-time 3D character model, and feeding back the comparison result to the master control system;
(5) the cloud server processes the image data acquired by the far-infrared thermal imaging heart rate detection module, calculates the fatigue degree of muscles of the user, and feeds the fatigue degree of the muscles back to the master control system;
(6) the main control system displays the real-time 3D character model and the standard 3D character model corresponding to the real-time 3D character model on the display module at the same time, and marks the parts of the user with irregular and standard body-building actions on the real-time 3D character model by different colors respectively; meanwhile, the master control system displays the fatigue degree of the muscles of the user on the real-time 3D character model in a color superposition mode;
(7) the user monitors the body building action of the user in real time through the display module, corrects wrong body building action in time, and decides whether to have a rest or not by monitoring the fatigue degree of muscles on the real-time 3D character model.
6. The real-time fitness monitoring method according to claim 5, wherein in the step (4), the 3D character model construction method comprises the following steps:
(4-1) after receiving the video image information transmitted by the master control system, the cloud server screens out the standard fitness actions of each stage of each fitness project and generates a standard 3D character model database which can be referred by a user and has the standard fitness actions of each fitness project;
(4-2) after the standard 3D character model database is constructed, the cloud server matches a corresponding standard 3D character model of the fitness item in a pre-established standard 3D character model database which stores the correct fitness action of each fitness item through processing and calculation according to the video image information of the current fitness action of the user; meanwhile, the cloud server generates a current real-time 3D character model of the user after processing video image information of the current body-building action of the user.
7. The real-time fitness monitoring method according to claim 5, wherein in step (1), the cloud server acquires the heart rate of the user through a thermal imaging-based non-contact heart rate detection method and feeds the heart rate back to the display module in real time, wherein the thermal imaging-based non-contact heart rate detection method comprises the following steps:
(1-1) converting the thermal imaging graph into a gray-scale graph by using an image processing technology, binarizing the converted gray-scale graph, and then primarily processing the binarized gray-scale graph by using a corrosion algorithm and an expansion algorithm;
(1-2) selecting a reserved human face and a naked neck region in the processed gray-scale image, and setting a lower 1/3 region of the face in the thermal imaging image as a region of interest to be tracked; obtaining the outline of a human body by using the boundary points of the minimum unit circle circumscribed picture, calculating and obtaining the range of the human face and the naked neck region and reserving the range;
(1-3) removing noise by using a wavelet denoising algorithm;
(1-4) processing the corresponding numerical value of the region of interest, and calculating the heart rate R of the user per minute, wherein the calculation formula is as follows:
R＝q×f×60/t
wherein t represents the current frame number, q represents the peak number of the signal after wavelet packet reconstruction, and f represents the sampling frequency of the video.
8. The real-time fitness monitoring method according to claim 5, wherein in step (5), the analysis of the degree of fatigue of the user's muscles comprises the steps of:
(5-1) the far infrared thermal imaging heart rate detection module collects a local body thermal imaging image of the fitness part of the user during movement and sends the local body thermal imaging image to the master control system;
(5-2) preprocessing the local body thermal imaging graph by the master control system, cutting the local thermal imaging graph of each heating area in the body-building part corresponding to the user, and sending the local thermal imaging graph to the cloud server;
(5-3) the cloud server inputs the local thermal imaging graph into a pre-trained first convolution neural network model, and a thermal imaging graph with heating of triceps is found in the multiple thermal imaging graphs through the first convolution neural network model;
(5-4) inputting the thermal imaging graph with the heating of the triceps into a second convolutional neural network model trained in advance, comparing the thermal imaging graph with the heating of the triceps when the user performs the fitness item with the thermal imaging graph with the heating of the triceps when the user performs the fitness item under the complete standard action through the second convolutional neural network model, and obtaining the matching degree of the thermal imaging graph and the thermal imaging graph;
(5-5) the cloud server further processes the triceps thermal imaging image output from the first convolution neural network model to obtain a temperature value of the image, and calibrates the temperature values obtained at all time points on the same coordinate axis to obtain a curve relating to temperature and time; the fatigue degree of the muscle is indirectly judged through the gradient value and the track of the curve, and a corresponding body-building scheme and a health safety prompt are obtained;
(5-6), superimposing the relevant body part of the exercise aimed at by the fitness equipment on the real-time 3D character model in a pattern mode; displaying the real-time 3D character model in a color superposition mode according to the matching degree correlation result; if the matching degree is higher than a preset value, displaying green in a relevant area in the real-time 3D character model, and if the matching degree is lower than the preset value, displaying red in the relevant area in the real-time 3D character model;
and (5-7) the master control system controls the display module to play the corresponding fitness scheme and fitness safety prompt, and displays the real-time 3D human body model in the display module.
9. The real-time fitness monitoring method according to claim 8, wherein in the step (5-3), the training method of the first convolutional neural network model comprises the following steps: the thermal imaging images of a large number of users after body building actions are collected respectively, the thermal imaging images of the triceps which generate heat when corresponding fitness equipment is cut out from the collected thermal imaging images are used as a training set, and the training set is subjected to learning training by using a neural network.
10. The real-time fitness monitoring method according to claim 8, wherein in the step (5-4), the training method of the second convolutional neural network model comprises the following steps: a large number of thermal imaging pictures of a human body after body-building action under complete standard action are collected respectively, thermal imaging pictures of triceps fever are cut out in the thermal imaging pictures, the thermal imaging pictures are used as a training set, and a neural network is used for learning and training the training set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010037410.9A CN111111111B (en) | 2020-01-14 | 2020-01-14 | Real-time body-building monitoring system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010037410.9A CN111111111B (en) | 2020-01-14 | 2020-01-14 | Real-time body-building monitoring system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111111111A true CN111111111A (en) | 2020-05-08 |
| CN111111111B CN111111111B (en) | 2023-06-23 |
Family
ID=70490799
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010037410.9A Active CN111111111B (en) | 2020-01-14 | 2020-01-14 | Real-time body-building monitoring system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111111111B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111579083A (en) * | 2020-05-13 | 2020-08-25 | 芋头科技（杭州）有限公司 | Body temperature measurement method and device based on infrared image face detection |
| CN111589091A (en) * | 2020-05-26 | 2020-08-28 | 许辉 | School sports test intelligent real-time monitoring management system based on big data |
| CN111860213A (en) * | 2020-06-29 | 2020-10-30 | 广州幻境科技有限公司 | Augmented reality system and control method thereof |
| CN112915494A (en) * | 2021-01-29 | 2021-06-08 | 重庆工程职业技术学院 | Sports gymnastics auxiliary system |
| CN113426080A (en) * | 2021-01-11 | 2021-09-24 | 吉首大学 | Dance physique training device and method |
| CN113749618A (en) * | 2021-09-10 | 2021-12-07 | 匠影(上海)智能科技有限公司 | Sports injury evaluation method, system, medium and terminal |
| CN113808446A (en) * | 2020-06-11 | 2021-12-17 | 华为技术有限公司 | Fitness course interaction method and related device |
| 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 |
| CN114334084A (en) * | 2022-03-01 | 2022-04-12 | 深圳市海清视讯科技有限公司 | Body-building data processing method, device, equipment and storage medium |
| CN114533045A (en) * | 2022-02-21 | 2022-05-27 | 首都体育学院 | Child physical activity grading method based on infrared thermal sensing imaging and human body part segmentation |
| CN114827660A (en) * | 2022-03-11 | 2022-07-29 | 华数传媒网络有限公司 | AI body-building system based on set-top box and implementation method |
| CN114984540A (en) * | 2022-06-10 | 2022-09-02 | 深圳信息职业技术学院 | Body-building exercise effect evaluation analysis management system based on artificial intelligence |
| CN115246338A (en) * | 2021-04-15 | 2022-10-28 | 陈进妹 | New energy automobile assistance-localization real-time parking charging system based on thing networking |
| CN116212355A (en) * | 2023-03-26 | 2023-06-06 | 北京卡路里信息技术有限公司 | Exercise instruction system and exercise instruction method |
| CN117198529A (en) * | 2023-08-31 | 2023-12-08 | 深圳市恒安特斯网络科技有限公司 | Moving image processing method, moving image processing device and readable storage medium |
| CN118021271A (en) * | 2024-01-31 | 2024-05-14 | 南京信息工程大学 | Body-building monitoring device and body-building monitoring method based on virtual reality |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110039659A1 (en) * | 2009-08-13 | 2011-02-17 | Sk C&C Co., Ltd. | User-Participating Type Fitness Lecture System and Fitness Training Method Using the Same |
| US20120165703A1 (en) * | 2010-12-22 | 2012-06-28 | Paul William Bottum | Preempt Muscle Map Screen |
| JP2013119001A (en) * | 2011-12-08 | 2013-06-17 | Asahi Sun Clean Co Ltd | Muscle fatigue evaluation device, system, method, and program |
| TWM474487U (en) * | 2013-12-05 | 2014-03-21 | Taiwan Hospitality & Tourism College | Exercise fatigue detection device |
| CN105561536A (en) * | 2015-12-17 | 2016-05-11 | 安徽寰智信息科技股份有限公司 | Man-machine interaction system having bodybuilding action correcting function |
| US20160302722A1 (en) * | 2015-04-14 | 2016-10-20 | Reham Ashkanani | Thermo detector to measure mass |
| US20170087416A1 (en) * | 2015-09-30 | 2017-03-30 | Board Of Trustees Of The University Of Alabama | Systems and methods for rehabilitation of limb motion |
| CN107050774A (en) * | 2017-05-17 | 2017-08-18 | 上海电机学院 | A kind of body-building action error correction system and method based on action collection |
| CN107341351A (en) * | 2017-07-06 | 2017-11-10 | 京东方科技集团股份有限公司 | Intelligent body-building method, apparatus and system |
| CN107551525A (en) * | 2017-10-18 | 2018-01-09 | 京东方科技集团股份有限公司 | Fitness-assisting system and method, body-building apparatus |
| CN109077704A (en) * | 2018-07-06 | 2018-12-25 | 上海玄众医疗科技有限公司 | A kind of infant nurses recognition methods and system |
| CN109106351A (en) * | 2018-09-25 | 2019-01-01 | 齐鲁工业大学 | A kind of human-body fatigue detection and slow-released system and method based on Internet of Things perception |
| JP2019005147A (en) * | 2017-06-23 | 2019-01-17 | 富士通株式会社 | Fatigue degree calculation device and fatigue degree calculation program |
| CN109480788A (en) * | 2018-09-11 | 2019-03-19 | 广州市妇女儿童医疗中心 | A kind of human skin epidermis and subdermal muscle layer three-dimensional infrared thermal imaging testing method |
| WO2019075824A1 (en) * | 2017-10-20 | 2019-04-25 | 深圳市鹰硕技术有限公司 | System for correcting and training running posture of child |
| US20190192913A1 (en) * | 2017-12-27 | 2019-06-27 | J-Mex Inc. | Method and system of planning fitness courses |
| CN110090422A (en) * | 2019-04-16 | 2019-08-06 | 湖南文理学院 | Body-building acts correcting system and body-building tournament system |
-
2020
- 2020-01-14 CN CN202010037410.9A patent/CN111111111B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110039659A1 (en) * | 2009-08-13 | 2011-02-17 | Sk C&C Co., Ltd. | User-Participating Type Fitness Lecture System and Fitness Training Method Using the Same |
| US20120165703A1 (en) * | 2010-12-22 | 2012-06-28 | Paul William Bottum | Preempt Muscle Map Screen |
| JP2013119001A (en) * | 2011-12-08 | 2013-06-17 | Asahi Sun Clean Co Ltd | Muscle fatigue evaluation device, system, method, and program |
| TWM474487U (en) * | 2013-12-05 | 2014-03-21 | Taiwan Hospitality & Tourism College | Exercise fatigue detection device |
| US20160302722A1 (en) * | 2015-04-14 | 2016-10-20 | Reham Ashkanani | Thermo detector to measure mass |
| US20170087416A1 (en) * | 2015-09-30 | 2017-03-30 | Board Of Trustees Of The University Of Alabama | Systems and methods for rehabilitation of limb motion |
| CN105561536A (en) * | 2015-12-17 | 2016-05-11 | 安徽寰智信息科技股份有限公司 | Man-machine interaction system having bodybuilding action correcting function |
| CN107050774A (en) * | 2017-05-17 | 2017-08-18 | 上海电机学院 | A kind of body-building action error correction system and method based on action collection |
| JP2019005147A (en) * | 2017-06-23 | 2019-01-17 | 富士通株式会社 | Fatigue degree calculation device and fatigue degree calculation program |
| CN107341351A (en) * | 2017-07-06 | 2017-11-10 | 京东方科技集团股份有限公司 | Intelligent body-building method, apparatus and system |
| CN107551525A (en) * | 2017-10-18 | 2018-01-09 | 京东方科技集团股份有限公司 | Fitness-assisting system and method, body-building apparatus |
| US20190111314A1 (en) * | 2017-10-18 | 2019-04-18 | Beijing Boe Optoelectronics Technology Co., Ltd. | Assistive fitness system and method, fitness equipment |
| WO2019075824A1 (en) * | 2017-10-20 | 2019-04-25 | 深圳市鹰硕技术有限公司 | System for correcting and training running posture of child |
| US20190192913A1 (en) * | 2017-12-27 | 2019-06-27 | J-Mex Inc. | Method and system of planning fitness courses |
| CN109077704A (en) * | 2018-07-06 | 2018-12-25 | 上海玄众医疗科技有限公司 | A kind of infant nurses recognition methods and system |
| CN109480788A (en) * | 2018-09-11 | 2019-03-19 | 广州市妇女儿童医疗中心 | A kind of human skin epidermis and subdermal muscle layer three-dimensional infrared thermal imaging testing method |
| CN109106351A (en) * | 2018-09-25 | 2019-01-01 | 齐鲁工业大学 | A kind of human-body fatigue detection and slow-released system and method based on Internet of Things perception |
| CN110090422A (en) * | 2019-04-16 | 2019-08-06 | 湖南文理学院 | Body-building acts correcting system and body-building tournament system |
Non-Patent Citations (2)
| Title |
|---|
| 徐晓龙;刘轶铭;吴宁馨;岳子谦;路正莲;: "基于Kinect 3D体感摄影机的健身教练***设计", 现代电子技术 * |
| 许嵩;王丽萍;: "基于红外技术的局部肌肉疲劳试验研究", 人类工效学 * |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111579083B (en) * | 2020-05-13 | 2022-06-07 | 芋头科技（杭州）有限公司 | Body temperature measuring method and device based on infrared image face detection |
| CN111579083A (en) * | 2020-05-13 | 2020-08-25 | 芋头科技（杭州）有限公司 | Body temperature measurement method and device based on infrared image face detection |
| CN111589091A (en) * | 2020-05-26 | 2020-08-28 | 许辉 | School sports test intelligent real-time monitoring management system based on big data |
| CN113808446B (en) * | 2020-06-11 | 2022-11-18 | 华为技术有限公司 | Fitness course interaction method and related device |
| CN113808446A (en) * | 2020-06-11 | 2021-12-17 | 华为技术有限公司 | Fitness course interaction method and related device |
| CN111860213A (en) * | 2020-06-29 | 2020-10-30 | 广州幻境科技有限公司 | Augmented reality system and control method thereof |
| CN113426080A (en) * | 2021-01-11 | 2021-09-24 | 吉首大学 | Dance physique training device and method |
| CN112915494A (en) * | 2021-01-29 | 2021-06-08 | 重庆工程职业技术学院 | Sports gymnastics auxiliary system |
| CN115246338A (en) * | 2021-04-15 | 2022-10-28 | 陈进妹 | New energy automobile assistance-localization real-time parking charging system based on thing networking |
| CN113749618A (en) * | 2021-09-10 | 2021-12-07 | 匠影(上海)智能科技有限公司 | Sports injury evaluation method, system, medium and terminal |
| CN113749618B (en) * | 2021-09-10 | 2023-12-22 | 匠影(上海)智能科技有限公司 | Sports injury assessment method, system, medium and terminal |
| 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 |
| CN114533045A (en) * | 2022-02-21 | 2022-05-27 | 首都体育学院 | Child physical activity grading method based on infrared thermal sensing imaging and human body part segmentation |
| CN114334084A (en) * | 2022-03-01 | 2022-04-12 | 深圳市海清视讯科技有限公司 | Body-building data processing method, device, equipment and storage medium |
| CN114334084B (en) * | 2022-03-01 | 2022-06-24 | 深圳市海清视讯科技有限公司 | Body-building data processing method, device, equipment and storage medium |
| CN114827660A (en) * | 2022-03-11 | 2022-07-29 | 华数传媒网络有限公司 | AI body-building system based on set-top box and implementation method |
| CN114984540B (en) * | 2022-06-10 | 2023-02-21 | 深圳信息职业技术学院 | Body-building exercise effect evaluation analysis management system based on artificial intelligence |
| CN114984540A (en) * | 2022-06-10 | 2022-09-02 | 深圳信息职业技术学院 | Body-building exercise effect evaluation analysis management system based on artificial intelligence |
| CN116212355A (en) * | 2023-03-26 | 2023-06-06 | 北京卡路里信息技术有限公司 | Exercise instruction system and exercise instruction method |
| CN117198529A (en) * | 2023-08-31 | 2023-12-08 | 深圳市恒安特斯网络科技有限公司 | Moving image processing method, moving image processing device and readable storage medium |
| CN118021271A (en) * | 2024-01-31 | 2024-05-14 | 南京信息工程大学 | Body-building monitoring device and body-building monitoring method based on virtual reality |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111111111B (en) | 2023-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111111111B (en) | Real-time body-building monitoring system and method | |
| EP3753489B1 (en) | Monitoring the performance of physical exercises | |
| CN107103298B (en) | Pull-up counting system and method based on image processing | |
| CN107767376A (en) | X-ray film stone age Forecasting Methodology and system based on deep learning | |
| Magalhaes et al. | Effectiveness of an automatic tracking software in underwater motion analysis | |
| US11663845B2 (en) | Method and apparatus for privacy protected assessment of movement disorder video recordings | |
| US20200279102A1 (en) | Movement monitoring system | |
| CN112464915B (en) | Push-up counting method based on human skeleton point detection | |
| WO2022088729A1 (en) | Point positioning method and related apparatus, and device, medium and computer program | |
| CN211962969U (en) | Body-building real-time monitoring system | |
| KR102013705B1 (en) | Apparatus and method for recognizing user's posture in horse-riding simulator | |
| CN117115922A (en) | Seat body forward-bending evaluation method, system, electronic equipment and storage medium | |
| CN115105062B (en) | Hip and knee joint coordination evaluation method, device and system and storage medium | |
| CN116543455A (en) | Method, equipment and medium for establishing parkinsonism gait damage assessment model and using same | |
| CN115568823A (en) | Method, system and device for evaluating human body balance ability | |
| CN113469055A (en) | Human body posture recognition system and human body posture recognition and evaluation method | |
| WO2016135560A2 (en) | Range of motion capture | |
| Lau et al. | Cost-benefit analysis reference framework for human motion capture and analysis systems | |
| CN112287840B (en) | Method and system for intelligently acquiring exercise capacity analysis data | |
| Malini | Non-Contact Heart Rate Monitoring System using Deep Learning Techniques | |
| CN114984540B (en) | Body-building exercise effect evaluation analysis management system based on artificial intelligence | |
| US20160249834A1 (en) | Range of motion capture | |
| Diwyanjalee et al. | Predicting Player’s Healthiness Using Machine Learning | |
| Uğurlu | Utilizing human-computer interaction data to extract user interests from web-based learning systems | |
| CN115814361A (en) | Intelligent fitness action detection and guidance method and 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 |