CN117274319A - Big data-based body-building exercise live broadcast method and system - Google Patents
Big data-based body-building exercise live broadcast method and system Download PDFInfo
- Publication number
- CN117274319A CN117274319A CN202311545515.5A CN202311545515A CN117274319A CN 117274319 A CN117274319 A CN 117274319A CN 202311545515 A CN202311545515 A CN 202311545515A CN 117274319 A CN117274319 A CN 117274319A
- Authority
- CN
- China
- Prior art keywords
- human body
- builder
- tracking frame
- data
- coach
- 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
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000009471 action Effects 0.000 claims abstract description 100
- 230000033001 locomotion Effects 0.000 claims abstract description 55
- 230000008569 process Effects 0.000 claims abstract description 32
- 238000012937 correction Methods 0.000 claims abstract description 15
- 238000012544 monitoring process Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000006073 displacement reaction Methods 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 8
- 230000036772 blood pressure Effects 0.000 claims description 4
- 230000029058 respiratory gaseous exchange Effects 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 210000002414 leg Anatomy 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 230000000241 respiratory effect Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 210000003414 extremity Anatomy 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004962 physiological condition Effects 0.000 description 1
- 210000000689 upper leg Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/21—Server components or server architectures
- H04N21/218—Source of audio or video content, e.g. local disk arrays
- H04N21/2187—Live feed
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
Abstract
The application discloses a body-building exercise live broadcast method and system based on big data, comprising the following steps: constructing an on-line body builder and live coach human body contour model; constructing a standard human body tracking frame matched with a body builder; establishing a three-dimensional coordinate system of a body builder human body contour model and a human body tracking frame, and recording initial coordinates of the body builder human body contour model and the human body tracking frame and initial distances between the body builder human body contour model and the human body tracking frame; dynamically tracking the outline of a human body in the movement process of a body builder, and monitoring physiological sign data in the movement process; acquiring deviation distance and physiological sign deviation data of a body builder in the exercise process; acquiring unqualified actions and inappropriate action of exercise intensity of a body builder; sending an action correction instruction or an intensity adjustment instruction to a coach end according to the statistical data; the instruction end makes corresponding adjustment to live broadcast sports according to the received instruction, and the live broadcast strength and live broadcast mode of action are adjusted in real time, so that the experience and satisfaction of online body-building people are improved.
Description
Technical Field
The application relates to a body-building live broadcast method and system based on big data, and belongs to the technical field of intelligent body-building.
Background
The intelligent body-building system is based on data acquisition of intelligent wearing equipment, and is supported by the Internet of things and cloud computing technology and processed by a big data analysis algorithm, so that a user can perform body-building more scientifically and reasonably. The intelligent body-building service system based on big data analysis has wide application prospect in the future, and for body-building lovers, the live broadcasting technology is already applied to intelligent body building at present, but for single-to-many intelligent body-building live broadcasting, because physiological signs and body characteristics of users are different, whether confirmation actions are accurately matched with the users or not cannot be realized in live broadcasting body-building exercises, and whether the real-time feedback actions have error requirements or not is difficult to realize, namely personalized guiding service cannot be accurately carried out, so that user experience is reduced.
Disclosure of Invention
In view of this, the application provides a body-building live broadcast method and system based on big data for solve above-mentioned prior art intelligence body-building live broadcast, unable accurate individuation is up to the service, thereby reduced the problem that user experience felt, the concrete scheme is:
according to one aspect of the application, there is provided a body-building live broadcast method based on big data, specifically including:
(1) Acquiring the number of people of the online body builder and the human body image data of the online body builder and the live-broadcast coach, and respectively constructing an online body builder human body contour model and a live-broadcast coach human body contour model;
(2) By comparing the on-line body builder human body contour model with the coach human body contour model, a standard human body tracking frame matched with the body builder is constructed;
(3) Respectively establishing a three-dimensional coordinate system of a body contour model of a body builder and a corresponding human body tracking frame, and respectively recording initial coordinates of the body contour model of the body builder and the human body tracking frame and initial distances between the body contour model of the body builder and the human body tracking frame;
(4) The human body tracking frame dynamically tracks the human body contour of the body builder in the movement process and monitors physiological sign data of the body builder in the movement process, wherein the center of the human body tracking frame is always kept coincident with the center of the human body contour when the human body tracking frame dynamically tracks;
(5) Acquiring deviation distance between the body contour of the body builder and a human body tracking frame in the movement process, and deviation data of physiological signs of the body builder;
(6) Obtaining unqualified actions of the body builder by comparing the deviation distance with a first preset value, and obtaining actions with unsuitable exercise intensity by comparing deviation data of physiological signs with a second preset value;
(7) Respectively counting the obtained unqualified actions and actions with unsuitable intensity, and sending an action correction instruction or an intensity adjustment instruction to a coach end when the counted value is larger than a set threshold value;
(8) And the coach side correspondingly adjusts the live action according to the received instruction.
Preferably, the initial distance is the distance between each point on the contour line of the body contour model of the exerciser and each point on the contour line of the corresponding body tracking frame;
the deviation distance comprises displacement deviation and time deviation;
the displacement deviation refers to the deviation between the offset distance and the initial distance between the point data on the human body outline of the body builder and the point data on the human body tracking frame when the body builder and the human body tracking frame make the same action in the movement process;
the time deviation refers to the time difference that the exerciser makes the same action with the human body tracking frame during the exercise.
Preferably, the physiological sign data includes heartbeat, blood pressure, and respiratory data.
Preferably, the first preset value is an action error range of the body builder and the human body tracking frame;
the second preset value is the normal variation range of the physiological sign of the body builder during exercise;
the set threshold is the ratio of the number of statistics to the number of online body-building people.
Preferably, the contour of the body tracking frame matches the shape of the body contour of the exerciser.
Preferably, ordering unqualified actions counted in the live broadcast process;
the ordering rules are as follows: the sequence of the unqualified actions is sorted according to the sequence of the number of the unqualified actions, so as to play a guiding role for the coach in next live broadcasting.
According to another aspect of the present application, there is provided a big data based exercise live broadcast system, the system comprising:
the acquisition module is respectively arranged at the training end and the body-building person end and is used for acquiring the number of the online body-building person and the human body image data of the online body-building person and the live-broadcast training;
the processing module is used for constructing a human body tracking frame matched with the body builder by comparing the human body contour model of the body builder with the human body contour model of the coach, and establishing a three-dimensional coordinate system of the human body contour model of the body builder and the corresponding human body tracking frame;
the monitoring module is used for acquiring the deviation distance between the human body outline of the body builder and the human body tracking frame in the movement process and the physiological sign data of the online body builder in the movement process, and transmitting the monitored data to the processing module;
the analysis module is used for carrying out statistics and analysis on the deviation distance and the physiological sign data sent by the received monitoring module, and specifically comprises the following steps:
judging whether the exercise of the body builder is qualified or not by comparing the deviation distance with a first preset value, and judging whether the exercise intensity is proper or not by comparing the deviation data of the physiological sign data with a second preset value;
respectively counting the number of unqualified actions and the number of actions with unsuitable movement intensity, and determining whether to send out an action correction instruction or a movement intensity adjustment instruction according to whether the counted number exceeds a set threshold value;
and the control module prompts the coach end to pause the next action when receiving the action correction instruction, and to re-demonstrate the current action, and prompts the coach end to rest or reduce the movement speed when receiving the movement strength large prompt instruction.
Preferably, the second preset value is a normal variation range of the physiological sign of the exerciser in motion, which is correspondingly acquired and matched with the exerciser, through calculation according to the physiological sign data of the exerciser, which is correspondingly acquired; the first preset value is an error range of the motion calculated by the processing module according to the initial distance between the human body contour model of the body builder and the corresponding human body tracking frame.
Preferably, the action correction instruction or the intensity prompt instruction is a voice prompt or a text prompt.
The beneficial effects that this application can produce include:
according to the method, the human body profile model of the online body builder and the human body profile model of the live-broadcast coach are compared, the standard human body tracking frame matched with the body state of the body builder is obtained through proportional conversion, in the live broadcast process, the standard actions made by the human body tracking frame and the actions made by the human body profile of the body builder are compared, counted and analyzed, the coach can decompose or conduct slow motion teaching aiming at the action with the greatest error in the online body builder group in the live broadcast process, so that the satisfaction degree of the online body builder is improved, and the motion strength is adjusted in real time according to the feedback of the data of the physiological signs monitored in the body building process;
meanwhile, the live broadcast speed or the exercise intensity of the next live broadcast is improved through data statistics in live broadcast, so that the body-building exercise live broadcast is more in line with the same audience group, personalized guiding service is realized in the live broadcast of the exercise with a plurality of people, and the body-building effect and the satisfaction degree of body-building persons are improved.
Drawings
FIG. 1 is a flow chart of a big data based exercise live broadcast method of the present application;
fig. 2 is a frame diagram of a body-building live broadcast system based on big data.
Detailed Description
The present application is described in detail below with reference to examples, but the present application is not limited to these examples.
The body-building exercise live broadcast method based on big data as shown in figure 1 specifically comprises the following steps:
(1) Acquiring the number of people of the online body-building person and the human body image data of the online body-building person and the live-broadcast coach by an infrared remote sensing scanner, and respectively constructing an online body-building person human body contour model and a live-broadcast coach human body contour model;
(2) By comparing the on-line body builder human body contour model with the coach human body contour model, a standard human body tracking frame matched with the body builder is constructed;
(3) Respectively establishing a three-dimensional coordinate system of a body contour model of a body builder and a corresponding human body tracking frame, and respectively recording initial coordinates of the body contour model of the body builder and the human body tracking frame and initial distances between the body contour model of the body builder and the human body tracking frame;
(4) The human body tracking frame dynamically tracks the human body contour of the body builder in the movement process and monitors physiological sign data of the body builder in the movement process, wherein the center of the human body tracking frame is always kept coincident with the center of the human body contour when the human body tracking frame dynamically tracks;
(5) Acquiring deviation distance between the body contour of the body builder and a human body tracking frame in the movement process and deviation data of physiological signs of the body builder through wearing equipment;
(6) The disqualified actions of the body builder are obtained by comparing the deviation distance with a first preset value, and actions with unsuitable exercise intensity are obtained by comparing the deviation data of the physiological signs with a second preset value;
(7) Respectively counting the obtained unqualified actions and actions with unsuitable intensity, and sending an action correction instruction or an intensity adjustment instruction to a coach end when the counted value is larger than a set threshold value;
(8) And the coach side correspondingly adjusts the live action according to the received instruction.
The method comprises the following steps: the coach end slows down the movement speed or pauses the rest according to the prompt so as to adapt to the movement intensity of the live online body builder, or performs decomposition action or slow action demonstration to correct the error or unqualified action.
The construction process of the human body tracking frame comprises the following steps:
firstly, scaling or amplifying an obtained human body contour model of a live-broadcast coach to obtain a human-shaped initial human body tracking frame; at least the head-to-sole distance in the initial body tracking frame is the same as the head-to-sole distance in the body contour model of the exerciser itself;
then, taking the midpoint of the connecting line from each joint point of the human body in the initial human body tracking frame to each joint point of the corresponding human body contour model of the body builder;
finally, connecting the midpoints in sequence according to the figure to obtain a standard human body tracking frame matched with the body builder;
the dynamic tracking process of the human body tracking frame is realized as follows: recording a three-dimensional coordinate system of a body contour model of a body builder and a corresponding human body tracking frame, and respectively recording initial coordinates of the body contour model and the human body tracking frame and initial distances between the body contour model and the human body tracking frame;
when in movement, firstly, the dynamic coordinates of the human body outline of the body builder are obtained, the displacement of the human body outline of the body builder is obtained after the dynamic coordinates are compared with the initial coordinates, the human body tracking frame is correspondingly adjusted, the center of the human body tracking frame is kept to coincide with the center of the human body outline model, and the distance between the human body tracking frame and the human body outline is always kept as the initial distance, and the specific implementation method is as follows:
setting a cross cursor at the center of the body contour of the body builder;
a plurality of punctuations are arranged on the contour line of the human body contour, and are respectively positioned at the main part and the main joint of the human body, such as: head, hand, arm, leg, foot, trunk, arm joint (armpit, elbow), leg joint (knee, thigh root), etc.;
recording initial three-dimensional coordinates of a cross cursor, establishing a three-dimensional coordinate system by taking a central point of the cross cursor as an origin, and respectively acquiring initial three-dimensional coordinates of each punctuation in the three-dimensional coordinate system;
because the center of the human body tracking frame is coincident with the center point of the cross cursor initially, displacement deviations delta x, delta y and delta z of the center point of the human body tracking frame relative to the center point of the cross cursor are obtained through conversion by tracking the position change of the center point of the cross cursor, the center position of the human body tracking frame is regulated by the obtained delta x, delta y and delta z, the center of the human body tracking frame is always coincident with the center point of the cross cursor, and the proportion that the human body tracking frame should be regulated is obtained through conversion of the distance and the angle from each mark point to the cross cursor, so that the distance between the human body tracking frame and the human body contour of a body builder is always kept to be the initial distance (here, the integral distance between the human body contour and the integral distance of the human body tracking frame).
Further, the initial distance is the distance between each point on the contour line of the body contour model of the body builder and each point on the contour line of the corresponding body tracking frame;
the deviation distance comprises displacement deviation and time deviation;
the displacement deviation refers to the deviation between the offset distance and the initial distance between the point data on the human body outline of the body builder and the point data on the human body tracking frame when the body builder and the human body tracking frame make the same action in the movement process;
the time deviation refers to the time difference that the exerciser makes the same action with the human body tracking frame during the exercise.
Further, the physiological sign data includes heartbeat, blood pressure, and respiratory data.
Further, the first preset value is an action error range of the body builder and the human body tracking frame;
the second preset value is the normal variation range of the physiological sign of the body builder during exercise;
the set threshold is the ratio of the number of statistics to the number of online body-building people.
Further, the contour of the human body tracking frame is matched with the shape of the human body contour of the body builder.
Further, ordering unqualified actions counted in the live broadcast process;
the ordering rules are as follows: the sequence of the unqualified actions is sorted according to the sequence of the number of the unqualified actions, so as to play a guiding role for the coach in next live broadcasting.
It should be noted that:
in the application, the human body image data of the online fitness person and the online live coach are acquired through an infrared remote sensing scanner;
then respectively constructing a body contour model of the body builder and a body contour model of the live coach through the acquired body image data;
the method comprises the steps of performing scaling of a human body contour model of an online body builder and a human body contour model of a live-broadcast coach to finally obtain a human body tracking frame matched with the body type of each online body builder, taking three-dimensional coordinates of each point on the contour line of the originally matched human body tracking frame as an original coordinate system, and taking the distance between the originally matched human body tracking frame and the human body contour model as an original distance;
in the motion process, the human body tracking frame acquires the demonstration action of a live coach through the system, and correspondingly makes the action the same as the coach after obtaining the instruction of the coach end;
the system compares the acquired human body contour image of the online body builder with the action image of the human body tracking frame, acquires the human body contour image of the online body builder through calculation, compares the offset distance between the human body tracking frame and each point data of the standard action image made by acquiring the live broadcast demonstration action image of the coach, and compares the offset distance with a first preset value (namely, the allowed action error distance range), if the offset distance exceeds the first preset value, the system records as unqualified actions, and counts, sorts and analyzes the number of the unqualified actions, wherein the sorting rule is sorting according to the order of the number of statistics from more to less;
in live broadcasting, if the counted number of some unqualified actions is larger than a set threshold, the system sends an action correction prompt instruction to a coach end, the coach end pauses the next action according to the action correction instruction, and decomposes the unqualified actions or carries out slow action teaching display until the acquired actions of the online body builder are displayed as being qualified, and then continues the next action;
the analysis process specifically comprises the following steps: and judging whether the unqualified motion is caused by too high speed of a live coach or too high difficulty of the motion according to the time difference between the corresponding motion made by the acquired online body builder and the motion made by the human body tracking frame. If the time of the online body builder to make the action lags behind the time of the human body tracking frame to make the same action and exceeds the allowable time range difference, the unqualified action is generalized into the live coach with too high speed;
if the time difference of the same action of the online body builder and the human body tracking frame is within the allowable range, unqualified actions are summarized as the action difficulty is overlarge;
after the live broadcast is finished, the coach end combines the analysis results according to the ordering sequence, and makes corresponding improvement in the next live broadcast, namely slow motion or decomposition display is performed if the motion difficulty is large; if the live speed is reduced because the speed is too fast.
Meanwhile, in the exercise process, respectively monitoring physiological sign data of each online body builder, acquiring physiological sign data such as blood pressure, heartbeat, respiration and the like of the body builder during exercise, respectively calculating deviation of the monitored physiological sign data and the physiological sign data of the body builder, as the deviation data of the physiological sign, comparing the deviation data of the physiological sign with a second preset value (namely, matching the normal variation range of the physiological sign of the body builder during exercise), and if the data of the physiological sign deviation calculated by the monitored physiological sign data is not in the second preset value, marking the action strength as obvious unsuitable action and analyzing the action;
if the physiological sign deviation data is larger than a second preset value, judging that the movement intensity of the action is overlarge, sending an intensity overlarge adjusting instruction to a training end, and enabling the training end to adjust the intensity by suspending rest or slowing down the speed;
if the physiological sign deviation data is smaller than a second preset value, judging that the exercise intensity is too small, and sending an intensity too small adjusting instruction to a live coach, wherein the coach side can properly increase the next intensity;
thereby keeping the fitness person in proper strength in normal live broadcast movement and improving the experience of the fitness person in live broadcast;
after the live broadcast is finished, the system correspondingly adjusts actions with unsuitable strength in the live broadcast according to the ordering sequence, specifically: the system records the regulation or change of the action of the coach, so that the original standard video in the system is updated, and the adaptive fitness video of a fitness group similar to the physiological condition of the fitness person is pushed out to the coach end according to the acquired related data of the online live player when the live player is live next time, so that the experience of the online fitness person in the next live broadcast is further improved.
A big data based exercise live broadcast system as shown in figure 2, said system comprising:
the acquisition module is respectively arranged at the training end and the body-building person end and is used for acquiring the number of the online body-building person and the human body image data of the online body-building person and the live-broadcast training;
the processing module is used for respectively constructing a human body contour model of the online body builder and a human body contour model of the coach, constructing a standard human body tracking frame matched with the body builder by comparing the human body contour model of the online body builder and the human body contour model of the coach, and establishing a three-dimensional coordinate system of the human body contour model of the body builder and the corresponding human body tracking frame;
the monitoring module is used for acquiring the deviation distance between the human body outline of the body builder and the human body tracking frame in the movement process and the physiological sign data of the online body builder in the movement process, and transmitting the monitored data to the processing module;
the analysis module is used for carrying out statistics and analysis on the deviation distance and the physiological sign data sent by the received monitoring module, and specifically comprises the following steps:
judging whether the exercise of the body builder is qualified or not by comparing the deviation distance with a first preset value, and judging whether the exercise intensity is proper or not by comparing the deviation data of the physiological sign data with a second preset value;
respectively counting the number of unqualified actions and the number of actions with unsuitable movement intensity, and determining whether to send out an action correction instruction or a movement intensity adjustment instruction according to whether the counted number exceeds a set threshold value;
and the control module prompts the coach end to pause the next action when receiving the action correction instruction, and to re-demonstrate the current action, and prompts the coach end to rest or reduce the movement speed when receiving the movement strength large prompt instruction.
Further, the second preset value is a change range of the physiological sign data of the corresponding matching body builder through calculation according to the physiological sign data of the corresponding acquired body builder by the processing module;
the first preset value is an error range at which the processing module calculates according to the initial distance between the body contour model of the exerciser and the corresponding body tracking frame.
Further, the action correction instruction or the strength prompt instruction is a voice prompt or a text prompt.
It should be noted that:
in this application, before live broadcast begins, gather the relevant information of coach and each body-building person through the equipment that is located coach end and each online body-building person end at first, then the system recommends the standard video that is suitable for this live broadcast crowd to the coach according to the information of each body-building person who obtains, specifically does: matching the movement of the corresponding body/limb actions according to the acquired body type characteristics of the body builder, and matching proper movement strength according to the acquired physiological data characteristics of the body builder;
the coach carries out demonstration according to the standard video of the system, the acquisition module acquires the action input of the coach and gives the action input to the control module, the control module shows the action input to each online body builder through the client, and the online body builder carries out movement according to the demonstration of the coach;
the equipment at the body builder side collects the movement conditions of all body builders in real time and sends the movement conditions to the processing module, and the processing module sends corresponding instructions to the controller according to the received corresponding information;
the controller receives the instruction and controls the device at the coaching end correspondingly, so that the coaching end can make corresponding adjustment.
The device of the body builder further comprises a wearing device, wherein the three-dimensional coordinates of the center of the body builder body contour model are positioned in real time through a positioning module arranged in the wearing device, and data of physiological signs of the body builder are acquired in real time through a functional module such as an ECG chip and an photoelectric sensor arranged in the wearing device.
The foregoing description is only a few examples of the present application and is not intended to limit the present application in any way, and although the present application is disclosed in the preferred examples, it is not intended to limit the present application, and any person skilled in the art may make some changes or modifications to the disclosed technology without departing from the scope of the technical solution of the present application, and the technical solution is equivalent to the equivalent embodiments.
Claims (9)
1. The body-building exercise live broadcast method based on big data is characterized by comprising the following steps of:
(1) Acquiring the number of people of the online body builder and the human body image data of the online body builder and the live-broadcast coach, and respectively constructing an online body builder human body contour model and a live-broadcast coach human body contour model;
(2) By comparing the on-line body builder human body contour model with the coach human body contour model, a standard human body tracking frame matched with the body builder is constructed;
(3) Respectively establishing a three-dimensional coordinate system of a body contour model of a body builder and a corresponding human body tracking frame, and respectively recording initial coordinates of the body contour model of the body builder and the human body tracking frame and initial distances between the body contour model of the body builder and the human body tracking frame;
(4) The human body tracking frame dynamically tracks the human body contour of the body builder in the movement process and monitors physiological sign data of the body builder in the movement process, wherein the center of the human body tracking frame is always kept coincident with the center of the human body contour when the human body tracking frame dynamically tracks;
(5) Acquiring deviation distance between the body contour of the body builder and a human body tracking frame in the movement process, and deviation data of physiological signs of the body builder;
(6) The disqualified actions of the body builder are obtained by comparing the deviation distance with a first preset value, and actions with unsuitable exercise intensity are obtained by comparing the deviation data of the physiological signs with a second preset value;
(7) Respectively counting the obtained unqualified actions and actions with unsuitable intensity, and sending an action correction instruction or an intensity adjustment instruction to a coach end when the counted value is larger than a set threshold value;
(8) And the coach side correspondingly adjusts the live action according to the received instruction.
2. The big data based body-building live broadcast method of claim 1, wherein the initial distance is a distance between points on a contour line of a body contour model of a body builder and points on a contour line of a corresponding body tracking frame;
the deviation distance comprises displacement deviation and time deviation;
the displacement deviation refers to the deviation between the offset distance and the initial distance between the point data on the human body outline of the body builder and the point data on the human body tracking frame when the body builder and the human body tracking frame make the same action in the movement process;
the time deviation refers to the time difference that the exerciser makes the same action with the human body tracking frame during the exercise.
3. The big data based exercise live method of claim 1, wherein the physiological sign data includes heart beat, blood pressure and respiration data.
4. The big data based exercise live broadcast method of claim 1, wherein the first preset value is: the action error range of the body builder and the human body tracking frame;
the second preset value is: normal variation range of physiological signs of a body builder during exercise;
the set threshold is: the ratio of the number of statistics to the number of online exercisers.
5. The direct exercise method based on big data according to claim 1, wherein the contour of the body tracking frame matches the shape of the body contour of the exerciser.
6. The big data-based fitness exercise live broadcast method of claim 1, wherein unqualified actions counted in the live broadcast process are ordered;
the ordering rules are as follows: the sequence of the unqualified actions is sorted according to the sequence of the number of the unqualified actions, so as to play a guiding role for the coach in next live broadcasting.
7. A big data based fitness sport live broadcast system, the system comprising:
the acquisition module is respectively arranged at the training end and the body-building person end and is used for acquiring the number of the online body-building person and the human body image data of the online body-building person and the live-broadcast training;
the processing module is used for respectively constructing a human body contour model of the online body builder and a human body contour model of the coach, constructing a standard human body tracking frame matched with the body builder by comparing the human body contour model of the online body builder and the human body contour model of the coach, and establishing a three-dimensional coordinate system of the human body contour model of the body builder and the corresponding human body tracking frame;
the monitoring module is used for acquiring the deviation distance between the human body outline of the body builder and the human body tracking frame in the movement process and the physiological sign data of the online body builder in the movement process, and transmitting the deviation distance and the monitored data to the processing module;
the analysis module is used for carrying out statistics and analysis on the deviation distance and the physiological sign data sent by the received monitoring module, and specifically comprises the following steps:
judging whether the exercise of the body builder is qualified or not by comparing the deviation distance with a first preset value, and judging whether the exercise intensity is proper or not by comparing the deviation data of the physiological sign data with a second preset value;
respectively counting the number of unqualified actions and the number of actions with unsuitable movement intensity, and determining whether to send out an action correction instruction or a movement intensity adjustment instruction according to whether the counted number exceeds a set threshold value;
and the control module prompts the coach end to pause the next action when receiving the action correction instruction, and to re-demonstrate the current action, and prompts the coach end to rest or reduce the movement speed when receiving the movement strength large prompt instruction.
8. The big data-based exercise live broadcast system of claim 7, wherein the second preset value is a normal variation range of the acquired physiological sign of the exerciser matched with the exerciser in exercise by calculating according to the acquired physiological sign data of the exerciser; the first preset value is an error range of the motion calculated by the processing module according to the initial distance between the human body contour model of the body builder and the corresponding human body tracking frame.
9. The big data based exercise live broadcast system of claim 7, wherein the motion correction instruction or the intensity cue instruction is a voice cue or a text cue.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311545515.5A CN117274319B (en) | 2023-11-20 | 2023-11-20 | Big data-based body-building exercise live broadcast method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311545515.5A CN117274319B (en) | 2023-11-20 | 2023-11-20 | Big data-based body-building exercise live broadcast method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117274319A true CN117274319A (en) | 2023-12-22 |
| CN117274319B CN117274319B (en) | 2024-01-30 |
Family
ID=89221876
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311545515.5A Active CN117274319B (en) | 2023-11-20 | 2023-11-20 | Big data-based body-building exercise live broadcast method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117274319B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017219276A1 (en) * | 2016-06-22 | 2017-12-28 | 深圳市屹石科技股份有限公司 | Personal trainer fitness service method and system, user end, trainer end, and processing method |
| CN108339236A (en) * | 2018-03-05 | 2018-07-31 | 北京踏行天际科技发展有限公司 | A kind of Spinning body-building teaching and training method |
| CN108492655A (en) * | 2018-03-05 | 2018-09-04 | 北京踏行天际科技发展有限公司 | A kind of Spinning body-building teaching and training platform |
| CN113761966A (en) * | 2020-06-01 | 2021-12-07 | 华为技术有限公司 | Motion adaptive synchronization method and electronic equipment |
| US20220203168A1 (en) * | 2020-12-29 | 2022-06-30 | Veki, Inc. | Systems and Methods for Enhancing Exercise Instruction, Tracking and Motivation |
| CN116266869A (en) * | 2021-12-17 | 2023-06-20 | 成都拟合未来科技有限公司 | Bidirectional identification method and system for body-building actions in live broadcast |
-
2023
- 2023-11-20 CN CN202311545515.5A patent/CN117274319B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017219276A1 (en) * | 2016-06-22 | 2017-12-28 | 深圳市屹石科技股份有限公司 | Personal trainer fitness service method and system, user end, trainer end, and processing method |
| CN108339236A (en) * | 2018-03-05 | 2018-07-31 | 北京踏行天际科技发展有限公司 | A kind of Spinning body-building teaching and training method |
| CN108492655A (en) * | 2018-03-05 | 2018-09-04 | 北京踏行天际科技发展有限公司 | A kind of Spinning body-building teaching and training platform |
| CN113761966A (en) * | 2020-06-01 | 2021-12-07 | 华为技术有限公司 | Motion adaptive synchronization method and electronic equipment |
| US20220203168A1 (en) * | 2020-12-29 | 2022-06-30 | Veki, Inc. | Systems and Methods for Enhancing Exercise Instruction, Tracking and Motivation |
| CN116266869A (en) * | 2021-12-17 | 2023-06-20 | 成都拟合未来科技有限公司 | Bidirectional identification method and system for body-building actions in live broadcast |
Non-Patent Citations (1)
| Title |
|---|
| 孙尚云;林仲志;吴水才;: "一种智慧健身教练系统的研制", 生命科学仪器, no. 06 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117274319B (en) | 2024-01-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107349594B (en) | A kind of action evaluation method of virtual Dance System | |
| CN109919034A (en) | A kind of identification of limb action with correct auxiliary training system and method | |
| CN108198601B (en) | Motion scoring method, device, equipment and storage medium | |
| CN108734104B (en) | Body-building action error correction method and system based on deep learning image recognition | |
| US7840031B2 (en) | Tracking a range of body movement based on 3D captured image streams of a user | |
| US9987520B2 (en) | Method and system for monitoring and feed-backing on execution of physical exercise routines | |
| US11633659B2 (en) | Systems and methods for assessing balance and form during body movement | |
| CN109692003B (en) | Training system is corrected to children gesture of running | |
| CN108853946A (en) | A kind of exercise guide training system and method based on Kinect | |
| WO2019082376A1 (en) | Motion state evaluation system, motion state evaluation device, motion state evaluation server, motion state evaluation method, and motion state evaluation program | |
| CN111652078A (en) | Yoga action guidance system and method based on computer vision | |
| CN103678859A (en) | Motion comparison method and motion comparison system | |
| US20180178060A1 (en) | Body motion analysis system, portable device and body motion analysis method | |
| CN113076002A (en) | Interconnected body-building competitive system and method based on multi-part action recognition | |
| CN110600125A (en) | Posture analysis assistant system based on artificial intelligence and transmission method | |
| CN114203275A (en) | Recovery state analysis system for rehabilitation training movement | |
| KR102013705B1 (en) | Apparatus and method for recognizing user's posture in horse-riding simulator | |
| CN117274319B (en) | Big data-based body-building exercise live broadcast method and system | |
| CN113262459A (en) | Method, apparatus and medium for determining motion standard of sport body-building mirror | |
| CN109718524B (en) | Shooting training system based on position | |
| CN113566396B (en) | Gymnasium temperature control and adjustment method based on data identification | |
| CN112818800A (en) | Physical exercise evaluation method and system based on human skeleton point depth image | |
| CN117109567A (en) | Riding gesture monitoring method and system for dynamic bicycle movement and wearable riding gesture monitoring equipment | |
| CN114376543B (en) | Method and system for adjusting motion combination scheme based on heart rate and motion feedback | |
| CN116637341A (en) | System and method for assisting physical exercise based on depth camera shooting technology |
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 |