CN109784178A - Parameter adjusting method, device and body-building equipment based on gesture identification - Google Patents
Parameter adjusting method, device and body-building equipment based on gesture identification Download PDFInfo
- Publication number
- CN109784178A CN109784178A CN201811536853.1A CN201811536853A CN109784178A CN 109784178 A CN109784178 A CN 109784178A CN 201811536853 A CN201811536853 A CN 201811536853A CN 109784178 A CN109784178 A CN 109784178A
- Authority
- CN
- China
- Prior art keywords
- heart rate
- body builder
- real
- facial image
- gesture path
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000033001 locomotion Effects 0.000 claims abstract description 37
- 230000001105 regulatory effect Effects 0.000 claims abstract description 16
- 238000001514 detection method Methods 0.000 claims abstract description 15
- 230000008859 change Effects 0.000 claims abstract description 10
- 230000001815 facial effect Effects 0.000 claims description 51
- 230000003068 static effect Effects 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 9
- 238000012163 sequencing technique Methods 0.000 claims description 8
- 230000004913 activation Effects 0.000 claims description 4
- 230000003213 activating effect Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 108010001267 Protein Subunits Proteins 0.000 description 2
- 210000000748 cardiovascular system Anatomy 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 210000003414 extremity Anatomy 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 210000000707 wrist Anatomy 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 210000004247 hand Anatomy 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The embodiment of the invention provides parameter adjusting method, device and body-building equipments based on gesture identification, this method comprises: the real-time heart rate of detection body builder;Judge the real-time heart rate of body builder whether within default heart rate range;If the real-time heart rate of body builder within default heart rate range, does not shoot the sport video of body builder;Sport video is pre-processed, images to be recognized frame sequence is obtained;It identifies at least one characteristic point on each picture frame in images to be recognized frame sequence, and according to the change in location of at least one characteristic point, arrives hand motion profile;Hand exercise track is matched respectively with preset multiple gesture paths, obtains target gesture path;The parameter of body-building equipment is adjusted according to regulating command corresponding to target gesture path, parameter includes speed and/or the gradient.Technical solution provided in an embodiment of the present invention is able to solve the problem of body-building equipment in the prior art is unable to adjust automatically parameter to meet the body-building demand of user.
Description
[technical field]
The present invention relates to video identification fields, more particularly to the parameter adjusting method based on gesture identification, device and body-building
Equipment.
[background technique]
Existing body-building equipment, such as treadmill, the mode for being manufactured almost exclusively by key carry out parameter setting and adjustment.People
During running, the key on treadmill is manually operated, the harmony and fluency of motion process can be destroyed, be easy to happen and fall
?.Body builder itself is also difficult to judge the body-building demand which velocity interval is suitble to oneself.
Existing body-building equipment has a drawback in that body-building equipment is unable to adjust automatically parameter to meet the body-building of user
Demand.
[summary of the invention]
In view of this, the embodiment of the invention provides parameter adjusting method, device and body-building equipment based on gesture identification,
To solve the problems, such as that body-building equipment is unable to adjust automatically parameter to meet the body-building demand of user in the prior art.
To achieve the goals above, according to an aspect of the invention, there is provided a kind of parameter tune based on gesture identification
Section method, which comprises
Detect the real-time heart rate of body builder;Judge the real-time heart rate of the body builder whether within default heart rate range;
If the real-time heart rate of the body builder within the default heart rate range, does not shoot the sport video of the body builder;
The sport video is pre-processed, images to be recognized frame sequence is obtained;It identifies every in the images to be recognized frame sequence
At least one characteristic point on a picture frame, and according at least one described characteristic point with the images to be recognized frame sequence when
Between change in location caused by sequence, arrive hand motion profile;By the hand exercise track and preset multiple gesture paths
It is matched respectively, obtains target gesture path, wherein the target gesture path is one in the multiple gesture path
It is a, and each gesture path is corresponding at least one regulating command;Referred to according to adjusting corresponding to the target gesture path
The parameter for adjusting body-building equipment is enabled, the parameter includes speed and/or the gradient.
Further, before whether the real-time heart rate for judging the body builder is within default heart rate range, institute
State method further include:
The user information of the body builder is obtained, the user information includes age, gender and static heart rate;According to described
User information calculates the default heart rate range.
Further, after whether the real-time heart rate for judging the body builder is within default heart rate range, and
And before the sport video of the shooting body builder, the method also includes:
If the real-time heart rate of the body builder not within the default heart rate range, exports the first information, described the
One information is for prompting the body builder to adjust the parameter.
Further, described that the sport video is pre-processed, obtain images to be recognized frame sequence, comprising:
Hand region image is extracted from each pre-set image frame of the sport video, obtains hand region image set
It closes;Adjust the big as low as uniform sizes of the hand region image in the hand region image collection;To hand area adjusted
Hand region image in area image set carries out median filter process, obtains the images to be recognized frame sequence.
Further, described to match the hand exercise track respectively with preset multiple gesture paths, it obtains
Target gesture path, comprising:
The hand exercise track is scaled to size identical as the gesture path;The hand exercise track after scaling
And the gesture path normalized is into the same coordinate system;Judge the phase of the hand exercise track and the gesture path
Whether it is greater than preset similarity threshold like degree;If so, determine that the hand exercise track is matched with the gesture path, and
The gesture path is confirmed as the target gesture path.
Further, before the real-time heart rate of the detection body builder, the method also includes:
Facial image to be identified is acquired, the facial image to be identified is the facial image of the body builder;Using default
Human face recognition model identify the facial image to be identified, obtain the feature vector of the facial image to be identified;It will be described
The feature vector of facial image to be identified is matched with the feature vector of multiple facial image samples in database, is obtained
With result, wherein user associated by the facial image sample has the access right of body-building equipment;It is tied according to the matching
Fruit judges whether the body builder has the access right of the body-building equipment, if so, activating the body-building equipment.
To achieve the goals above, according to an aspect of the invention, there is provided a kind of parameter tune based on gesture identification
Regulating device, described device include: detection unit, for detecting the real-time heart rate of body builder;Judging unit, it is described strong for judging
Whether the real-time heart rate of body person is within default heart rate range;First acquisition unit, if the real-time heart for the body builder
Rate within the default heart rate range, does not then shoot the sport video of the body builder;Processing unit, for the movement
Video is pre-processed, and images to be recognized frame sequence is obtained;First recognition unit, for identification the images to be recognized frame sequence
In each picture frame at least one characteristic point, and according at least one described characteristic point with the images to be recognized frame sequence
Change in location caused by the time sequencing of column obtains hand exercise track;First matching unit is used for the hand exercise
Track is matched respectively with preset multiple gesture paths, obtains target gesture path, wherein each gesture path at least
One regulating command is corresponding;Unit is adjusted, adjusts body-building for the regulating command according to corresponding to the target gesture path
The parameter of equipment, the parameter include speed and/or the gradient.
Further, described device further include:
Second acquisition unit, for obtaining the user information of the body builder, the user information include the age, gender and
Static heart rate;Computing unit, for calculating the default heart rate range according to the user information.
Further, described device further include:
Acquisition unit, for acquiring facial image to be identified, the facial image to be identified is the face of the body builder
Image;Second recognition unit, for identifying the facial image to be identified using preset human face recognition model, obtain it is described to
Identify the feature vector of facial image;Second matching unit, for by the feature vector and data of the facial image to be identified
The feature vector of multiple facial image samples in library is matched, and matching result is obtained, wherein the facial image sample institute
Associated user has the access right of body-building equipment;Unit is activated, for judging the body builder according to the matching result
Whether there is the access right of the body-building equipment, if so, activating the body-building equipment.
To achieve the goals above, according to an aspect of the invention, there is provided a kind of body-building equipment, including above-mentioned base
In the parameter adjustment control of gesture identification.
In the present solution, by detection body builder real-time heart rate, judge real-time heart rate whether default heart rate range it
It is interior, to determine whether to reach body-building demand, and according to the gesture motion of body builder, the parameter of body-building equipment is automatically adjusted, so that
The real-time heart rate of body builder is adjusted with the variation of motion state to default heart rate range, to keep optimal movement state.From
And solve the problems, such as that body-building equipment is unable to adjust automatically parameter to meet the body-building demand of user in the prior art.
[Detailed description of the invention]
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for this field
For those of ordinary skill, without any creative labor, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is a kind of flow chart of parameter adjusting method based on gesture identification according to an embodiment of the present invention;
Fig. 2 is a kind of schematic diagram of parameter adjustment control based on gesture identification according to an embodiment of the present invention.
[specific embodiment]
For a better understanding of the technical solution of the present invention, being retouched in detail to the embodiment of the present invention with reference to the accompanying drawing
It states.
It will be appreciated that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Base
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts it is all its
Its embodiment, shall fall within the protection scope of the present invention.
The term used in embodiments of the present invention is only to be not intended to be limiting merely for for the purpose of describing particular embodiments
The present invention.In the embodiment of the present invention and the "an" of singular used in the attached claims, " described " and "the"
It is also intended to including most forms, unless the context clearly indicates other meaning.
It should be appreciated that term "and/or" used herein is only a kind of incidence relation for describing affiliated partner, indicate
There may be three kinds of relationships, for example, A and/or B, can indicate: individualism A, exist simultaneously A and B, individualism B these three
Situation.In addition, character "/" herein, typicallys represent the relationship that forward-backward correlation object is a kind of "or".
It will be appreciated that though terminal may be described using term first, second, third, etc. in embodiments of the present invention,
But these terminals should not necessarily be limited by these terms.These terms are only used to for terminal being distinguished from each other out.For example, not departing from the present invention
In the case where scope of embodiments, first acquisition unit can also be referred to as second acquisition unit, similarly, second acquisition unit
First acquisition unit can be referred to as.
Depending on context, word as used in this " if " can be construed to " ... when " or " when ...
When " or " in response to determination " or " in response to detection ".Similarly, depend on context, phrase " if it is determined that " or " if detection
(condition or event of statement) " can be construed to " when determining " or " in response to determination " or " when the detection (condition of statement
Or event) when " or " in response to detection (condition or event of statement) ".
Fig. 1 is a kind of flow chart of parameter adjusting method based on gesture identification according to an embodiment of the present invention, such as Fig. 1 institute
Show, this method comprises:
Step S101 detects the real-time heart rate of body builder.
Whether step S102 judges the real-time heart rate of body builder within default heart rate range.
Step S103, if the real-time heart rate of body builder shoots the movement of body builder not within default heart rate range
Video.
Step S104, pre-processes sport video, obtains images to be recognized frame sequence.
Step S105, identify images to be recognized frame sequence in each picture frame at least one characteristic point, and according to
Change in location caused by time sequencing of at least one characteristic point with images to be recognized frame sequence arrives hand motion profile.
Hand exercise track is matched respectively with preset multiple gesture paths, obtains target gesture by step S106
Track, wherein target gesture path is one in multiple gesture paths, and each gesture path and at least one regulating command
It is corresponding.
Step S107, the parameter of body-building equipment is adjusted according to regulating command corresponding to target gesture path, and parameter includes
Speed and/or the gradient.
Wherein, characteristic point quantity can have multiple, such as wrist characteristic point, fingertip characteristic point of each finger etc..
Optionally, at least one characteristic point on each picture frame in images to be recognized frame sequence is identified, and according to extremely
The mode of change in location caused by few time sequencing of the characteristic point with images to be recognized frame sequence, may call upon limbs
Language identification model identified, body language identification model can be DensePose, OpenPose, AlphaPose and
Any one in DeepPose.
In the present solution, by detection body builder real-time heart rate, judge real-time heart rate whether default heart rate range it
It is interior, to determine whether to reach body-building demand, and according to the gesture motion of body builder, the parameter of body-building equipment is automatically adjusted, so that
The real-time heart rate of body builder is adjusted with the variation of motion state to default heart rate range, to keep optimal movement state.From
And solve the problems, such as that body-building equipment is unable to adjust automatically parameter to meet the body-building demand of user in the prior art.
Wherein, the real-time heart rate of body builder can be obtained by the collector worn with body builder, can also be by collector
It is integrally disposed on body-building equipment, such as at handle.
Optionally, before whether the real-time heart rate for judging body builder is within default heart rate range, method further include: obtain
The user information of body builder is taken, user information includes age, gender and static heart rate;Default heart rate model is calculated according to user information
It encloses.
Wherein, heart rate range (male)=(210- static state heart rate-age) * (0.6~0.8)+static state heart rate is preset;It is default
Heart rate range (women)=((210- static state heart rate-age) * (0.6~0.8)+static state heart rate) * 0.95.It is to be appreciated that pre-
If the heart rate range movement heart effectively safe when being function of the body-building user by aerobic exercise raising Cardiovascular System
Rate.When the real-time heart rate of body builder exceeds default heart rate range, suitably slowly and movement range should be reduced;When the real-time heart
When rate is excessively slow, it can suitably accelerate speed and increase movement range.
Optionally, after whether the real-time heart rate for judging body builder is within default heart rate range, also, it is strong in shooting
Before the sport video of body person, method further include: if the real-time heart rate of body builder not within default heart rate range, output the
One information, the first information is for prompting body builder's adjustment parameter.
Wherein, export the first information mode can there are many.Such as: mode one, in the interactive screen of body-building equipment
Show the first information, prompt the real-time motion state of body builder, body builder after receiving the first information, can voluntarily select be
No carry out parameter regulation.Such as: it prompts to accelerate towards the arrow on the right, prompts to slow down towards the arrow on the left side, towards top
Arrow prompt increases the gradient, prompts grading towards following arrow, prompts while increasing towards the arrow at 45 degree of angles of upper right
Speed and the gradient prompt towards the arrow at 45 degree of upper left angle while slowing down and increasing the gradient, mention towards the arrow at the 45 degree of angles in bottom right
Show while increasing speed and grading, slows down simultaneously simultaneously grading towards the arrow prompt at 45 degree of lower-left angle.Mode two is good for
The sound box system of body equipment audibly exports the first information.
Optionally, sport video is pre-processed, obtains images to be recognized frame sequence, comprising: from the every of sport video
Hand region image is extracted in one pre-set image frame, obtains hand region image collection;It adjusts in hand region image collection
The big as low as uniform sizes of hand region image;To in the hand region image progress in hand region image collection adjusted
Value filtering processing, obtains images to be recognized frame sequence.
Wherein, pre-set image frame can be according to default video frame rate and default sampling Rule.Specifically, pre- setting video
Frame per second is 30 frames/second, can choose the 1st, 10,20,30 frame images.And using the 1st, 10,20,30 frame images as pre-set image frame
Hand region image is extracted one by one.It is to be appreciated that evenly spaced multiple images is selected to extract, can accelerate to extract speed
Rate, and then accelerate later period recognition efficiency.The number of image frames of selection is more, be spaced it is shorter, obtained motion profile with it is more accurate.
Optionally, hand exercise track is matched respectively with preset multiple gesture paths, obtains target gesture rail
Mark, comprising:
Hand exercise track is scaled to size identical as gesture path;Hand motion profile and gesture path after scaling are returned
One changes processing into the same coordinate system;Judge whether the similarity of hand exercise track and gesture path is greater than preset similarity
Threshold value;If so, determining that hand exercise track is matched with gesture path, and gesture path is confirmed as target gesture path.
It is to be appreciated that the gesture motion by identification body builder about instruction adjustment parameter, so that body builder is moving
It, will not without brandishing hand according to the first information, the parameter regulation of body-building equipment can be realized by manual key under state
Destroy the harmony and fluency of motion process.
Optionally, after the parameter that the regulating command according to corresponding to target gesture path adjusts body-building equipment, method
Further include: the history audio for obtaining body builder plays record;It is played and is recorded according to history audio, identify the label of history audio;
Based on the label of the history audio recognized, the music to match with label is obtained from cloud;Play the music got.To
The music that body builder likes can be played automatically, provides music to body builder during body-building, and user can be helped to alleviate fortune
Dynamic bring fatigue, improves exercise experience, more personalized.
Optionally, before the real-time heart rate of detection body builder, method further include: facial image to be identified is acquired, wait know
Others' face image is the facial image of body builder;Facial image to be identified is identified using preset human face recognition model, obtain to
Identify the feature vector of facial image;By multiple facial image samples in the feature vector and database of facial image to be identified
Feature vector matched, obtain matching result, wherein there is body-building equipment to make by user associated by facial image sample
Use permission;According to matching result, judge whether body builder has the access right of body-building equipment, if so, activation body-building equipment.
Body-building equipment is activated by face recognition technology, body-building equipment is managed without other access control systems, so that having
The direct brush face of the user of access right can body-building, improve the efficiency of management of body-building equipment.
Optionally, by multiple face training samples training Initial Face identification model, and further Initial Face is known
The output result of other model inputs the discrimination model pre-established, is instructed by the confrontation of discrimination model and Initial Face identification model
Practice, obtains the human face recognition model of deep learning.Wherein, Initial Face identification model, which can be, utilizes machine learning method and instruction
Practice sample to carry out obtained from Training existing convolutional neural networks structure.Trained human face recognition model can
For recognition of face, and the accuracy of recognition of face can be effectively improved, to further increase the efficiency of management of body-building equipment.
The embodiment of the invention provides a kind of parameter adjustment control based on gesture identification, the device is for executing above-mentioned base
In the parameter adjusting method of gesture identification, as shown in Fig. 2, the device includes: detection unit 10, the acquisition of judging unit 20, first
Unit 30, the first recognition unit 50, the first matching unit 60, adjusts unit 70 at processing unit 40.
Detection unit 10, for detecting the real-time heart rate of body builder;
Judging unit 20, for judging the real-time heart rate of body builder whether within default heart rate range;
First acquisition unit 30, if the real-time heart rate for body builder is not within default heart rate range, shooting is strong
The sport video of body person;
Processing unit 40 obtains images to be recognized frame sequence for pre-processing to sport video;
First recognition unit 50, for identification at least one feature on each picture frame in images to be recognized frame sequence
Point, and the change in location according to caused by time sequencing of at least one characteristic point with images to be recognized frame sequence, obtain hand
Motion profile;
First matching unit 60 is obtained for matching hand exercise track respectively with preset multiple gesture paths
To target gesture path, wherein each gesture path is corresponding at least one regulating command;
Unit 70 is adjusted, the parameter of body-building equipment, ginseng are adjusted for the regulating command according to corresponding to target gesture path
Number includes speed and/or the gradient.
Wherein, characteristic point quantity can have multiple, such as wrist characteristic point, fingertip characteristic point of each finger etc..
Optionally, at least one characteristic point on each picture frame in images to be recognized frame sequence is identified, and according to extremely
The mode of change in location caused by few time sequencing of the characteristic point with images to be recognized frame sequence, may call upon limbs
Language identification model identified, body language identification model can be DensePose, OpenPose, AlphaPose and
Any one in DeepPose.
In the present solution, by detection body builder real-time heart rate, judge real-time heart rate whether default heart rate range it
It is interior, to determine whether to reach body-building demand, and according to the gesture motion of body builder, the parameter of body-building equipment is automatically adjusted, so that
The real-time heart rate of body builder is adjusted with the variation of motion state to default heart rate range, to keep optimal movement state.From
And solve the problems, such as that body-building equipment is unable to adjust automatically parameter to meet the body-building demand of user in the prior art.
Wherein, the real-time heart rate of body builder can be obtained by the collector worn with body builder, can also be by collector
It is integrally disposed on body-building equipment, such as at handle.
Optionally, body-building equipment further include: second acquisition unit, computing unit.
Second acquisition unit, for obtaining the user information of body builder, user information includes age, gender and the static heart
Rate;Computing unit, for calculating default heart rate range according to user information.
Wherein, heart rate range (male)=(210- static state heart rate-age) * (0.6~0.8)+static state heart rate is preset;It is default
Heart rate range (women)=((210- static state heart rate-age) * (0.6~0.8)+static state heart rate) * 0.95.It is to be appreciated that pre-
If the heart rate range movement heart effectively safe when being function of the body-building user by aerobic exercise raising Cardiovascular System
Rate.When the real-time heart rate of body builder exceeds default heart rate range, suitably slowly and movement range should be reduced;When the real-time heart
When rate is excessively slow, it can suitably accelerate speed and increase movement range.
Optionally, body-building equipment further include: the first output unit, if the real-time heart rate for body builder is not in the default heart
Within the scope of rate, the first information is exported, the first information is for prompting body builder's adjustment parameter.
Wherein, export the first information mode can there are many.Such as: mode one, in the interactive screen of body-building equipment
Show the first information, prompt the real-time motion state of body builder, body builder after receiving the first information, can voluntarily select be
No carry out parameter regulation.Such as: it prompts to accelerate towards the arrow on the right, prompts to slow down towards the arrow on the left side, towards top
Arrow prompt increases the gradient, prompts grading towards following arrow, prompts while increasing towards the arrow at 45 degree of angles of upper right
Speed and the gradient prompt towards the arrow at 45 degree of upper left angle while slowing down and increasing the gradient, mention towards the arrow at the 45 degree of angles in bottom right
Show while increasing speed and grading, slows down simultaneously simultaneously grading towards the arrow prompt at 45 degree of lower-left angle.Mode two is good for
The sound box system of body equipment audibly exports the first information.
Optionally, processing unit 40 includes extracting subelement, adjustment subelement, processing subelement.
Subelement is extracted, for extracting hand region image from each pre-set image frame of sport video, obtains hand
Area image set;Subelement is adjusted, for adjusting the big as low as unified of the hand region image in hand region image collection
Size;Subelement is handled, for carrying out at median filtering to the hand region image in hand region image collection adjusted
Reason, obtains images to be recognized frame sequence.
Wherein, pre-set image frame can be according to default video frame rate and default sampling Rule.Specifically, pre- setting video
Frame per second is 30 frames/second, can choose the 1st, 10,20,30 frame images.And using the 1st, 10,20,30 frame images as pre-set image frame
Hand region image is extracted one by one.It is to be appreciated that evenly spaced multiple images is selected to extract, can accelerate to extract speed
Rate, and then accelerate later period recognition efficiency.The number of image frames of selection is more, be spaced it is shorter, obtained motion profile with it is more accurate.
Optionally, the first matching unit 60 includes scaling subelement, normalized subelement, judgment sub-unit, determination
Subelement, second obtain subelement.
Subelement is scaled, for scaling hand exercise track to size identical as gesture path;Normalized subelement,
For hand motion profile after scaling and gesture path normalized into the same coordinate system;Judgment sub-unit, for sentencing
Whether the similarity for portion's motion profile and the gesture path of cutting off the hands is greater than preset similarity threshold;Determine subelement, be used for if so,
It determines that hand exercise track is matched with gesture path, and gesture path is confirmed as target gesture path.
It is to be appreciated that the gesture motion by identification body builder about instruction adjustment parameter, so that body builder is moving
It, will not without brandishing hand according to the first information, the parameter regulation of body-building equipment can be realized by manual key under state
Destroy the harmony and fluency of motion process.
Optionally, device further include: acquisition unit, the second recognition unit, the second matching unit, activation unit.
Acquisition unit, for acquiring facial image to be identified, facial image to be identified is the facial image of body builder;Second
Recognition unit obtains the spy of facial image to be identified for identifying facial image to be identified using preset human face recognition model
Levy vector;Second matching unit, for by multiple facial image samples in the feature vector and database of facial image to be identified
This feature vector is matched, and matching result is obtained, wherein user associated by facial image sample has body-building equipment
Access right;Unit is activated, for judging whether body builder has the access right of body-building equipment according to matching result, if so,
Activate body-building equipment.Body-building equipment is activated by face recognition technology, manages body-building equipment without other access control systems, so that
The direct brush face of user with access right can body-building, improve the efficiency of management of body-building equipment.
Optionally, device further include: third acquiring unit, third recognition unit, the 4th acquiring unit, broadcast unit.The
Three acquiring units, the history audio for obtaining body builder play record;Third recognition unit, for being played according to history audio
Record identifies the label of history audio;4th acquiring unit is obtained for the label based on the history audio recognized from cloud
Take the music to match with label;Broadcast unit, for playing the music got.Like so as to play body builder automatically
Music, during body-building give body builder provide music, can help user alleviate movement bring fatigue, improve body-building body
It tests, it is more personalized.
The embodiment of the invention provides a kind of storage medium, storage medium includes the program of storage, wherein is run in program
When control storage medium where equipment execute following steps:
Detect the real-time heart rate of body builder;Judge the real-time heart rate of body builder whether within default heart rate range;If
The real-time heart rate of body builder within default heart rate range, does not then shoot the sport video of body builder;Sport video is carried out pre-
Processing, obtains images to be recognized frame sequence;Identify at least one feature on each picture frame in images to be recognized frame sequence
Point, and the change in location according to caused by time sequencing of at least one characteristic point with images to be recognized frame sequence are transported to hand
Dynamic rail mark;Hand exercise track is matched respectively with preset multiple gesture paths, obtains target gesture path, wherein
Target gesture path is one in multiple gesture paths, and each gesture path is corresponding at least one regulating command;Root
The parameter of body-building equipment is adjusted according to regulating command corresponding to target gesture path, parameter includes speed and/or the gradient.
Optionally, when program is run, equipment where control storage medium also executes following steps: obtaining the use of body builder
Family information, user information include age, gender and static heart rate;Default heart rate range is calculated according to user information.
Optionally, when program is run, equipment where control storage medium also executes following steps: from the every of sport video
Hand region image is extracted in one pre-set image frame, obtains hand region image collection;It adjusts in hand region image collection
The big as low as uniform sizes of hand region image;To in the hand region image progress in hand region image collection adjusted
Value filtering processing, obtains images to be recognized frame sequence.
Optionally, when program is run, equipment where control storage medium also executes following steps: scaling hand exercise rail
Mark extremely size identical as gesture path;Will after scaling hand motion profile and gesture path normalized to the same coordinate system
In;Judge whether the similarity of hand exercise track and gesture path is greater than preset similarity threshold;If so, determining hand
Motion profile is matched with gesture path, and gesture path is confirmed as target gesture path.
Optionally, when program is run, equipment where control storage medium also executes following steps: acquiring face to be identified
Image, facial image to be identified are the facial image of body builder;Face figure to be identified is identified using preset human face recognition model
Picture obtains the feature vector of facial image to be identified;By multiple people in the feature vector and database of facial image to be identified
The feature vector of face image sample is matched, and matching result is obtained, wherein user associated by facial image sample has strong
The access right of body equipment;According to matching result, judge whether body builder has the access right of body-building equipment, if so, activation
Body-building equipment.
The embodiment of the invention provides a kind of body-building equipments, including the above-mentioned parameter adjustment control based on gesture identification.
It should be noted that terminal involved in the embodiment of the present invention can include but is not limited to personal computer
(PersonalComputer, PC), personal digital assistant (PersonalDigital Assistant, PDA), wireless handheld are set
Standby, tablet computer (Tablet Computer), mobile phone, MP3 player, MP4 player etc..
It is understood that the application can be mounted in the application program (nativeApp) in terminal, or may be used also
To be a web page program (webApp) of browser in terminal, the embodiment of the present invention is to this without limiting.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided by the present invention, it should be understood that disclosed system, device and method can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only a kind of logical function partition, there may be another division manner in actual implementation, for example, multiple units or group
Part can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown
Or the mutual coupling, direct-coupling or communication connection discussed can be through some interfaces, device or unit it is indirect
Coupling or communication connection can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of hardware adds SFU software functional unit.
The above-mentioned integrated unit being realized in the form of SFU software functional unit can store and computer-readable deposit at one
In storage media.Above-mentioned SFU software functional unit is stored in a storage medium, including some instructions are used so that a computer
It is each that device (can be personal computer, server or network equipment etc.) or processor (Processor) execute the present invention
The part steps of embodiment the method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (Read-
Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. it is various
It can store the medium of program code.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Within mind and principle, any modification, equivalent substitution, improvement and etc. done be should be included within the scope of the present invention.
Claims (10)
1. a kind of parameter adjusting method based on gesture identification, which is characterized in that the described method includes:
Detect the real-time heart rate of body builder;
Judge the real-time heart rate of the body builder whether within default heart rate range;
If the real-time heart rate of the body builder not within the default heart rate range, shoots the movement view of the body builder
Frequently;
The sport video is pre-processed, images to be recognized frame sequence is obtained;
Identify at least one characteristic point on each picture frame in the images to be recognized frame sequence, and according to described at least one
Change in location caused by time sequencing of a characteristic point with the images to be recognized frame sequence, obtains hand exercise track;
The hand exercise track is matched respectively with preset multiple gesture paths, obtains target gesture path, wherein
The target gesture path is one in the multiple gesture path, and each gesture path and at least one regulating command phase
It is corresponding;
The parameter of body-building equipment is adjusted according to regulating command corresponding to the target gesture path, the parameter includes speed
And/or the gradient.
2. the method according to claim 1, wherein the real-time heart rate for judging the body builder whether
Before within default heart rate range, the method also includes:
The user information of the body builder is obtained, the user information includes age, gender and static heart rate;
The default heart rate range is calculated according to the user information.
3. the method according to claim 1, wherein the real-time heart rate for judging the body builder whether
After within default heart rate range, also, before the sport video of the shooting body builder, the method also includes:
If the real-time heart rate of the body builder not within the default heart rate range, exports the first information, first letter
Breath is for prompting the body builder to adjust the parameter.
4. the method according to claim 1, wherein described pre-process the sport video, obtain to
Identify image frame sequence, comprising:
Hand region image is extracted from each pre-set image frame of the sport video, obtains hand region image collection;
Adjust the big as low as uniform sizes of the hand region image in the hand region image collection;
Median filter process is carried out to the hand region image in hand region image collection adjusted, is obtained described to be identified
Image frame sequence.
5. the method according to claim 1, wherein described by the hand exercise track and preset multiple hands
Gesture track is matched respectively, obtains target gesture path, comprising:
The hand exercise track is scaled to size identical as the gesture path;
The hand exercise track and the gesture path normalized are into the same coordinate system after scaling;
Judge whether the hand exercise track and the similarity of the gesture path are greater than preset similarity threshold;
If so, determine that the hand exercise track is matched with the gesture path, and described in the gesture path is confirmed as
Target gesture path.
6. method described in any one of -5 according to claim 1, which is characterized in that in the real-time heart of the detection body builder
Before rate, the method also includes:
Facial image to be identified is acquired, the facial image to be identified is the facial image of the body builder;
The facial image to be identified is identified using preset human face recognition model, obtains the feature of the facial image to be identified
Vector;
The feature vector of multiple facial image samples in the feature vector and database of the facial image to be identified is carried out
Matching, obtains matching result, wherein user associated by the facial image sample has the access right of body-building equipment;
According to the matching result, judge whether the body builder has the access right of the body-building equipment, if so, activation institute
State body-building equipment.
7. a kind of parameter adjustment control based on gesture identification, which is characterized in that described device includes:
Detection unit, for detecting the real-time heart rate of body builder;
Judging unit, for judging the real-time heart rate of the body builder whether within default heart rate range;
First acquisition unit, if the real-time heart rate for the body builder is shot not within the default heart rate range
The sport video of the body builder;
Processing unit obtains images to be recognized frame sequence for pre-processing to the sport video;
First recognition unit, for identification at least one feature on each picture frame in the images to be recognized frame sequence
Point, and the change in location according to caused by time sequencing of at least one the described characteristic point with the images to be recognized frame sequence,
Obtain hand exercise track;
First matching unit is obtained for matching the hand exercise track respectively with preset multiple gesture paths
Target gesture path, wherein each gesture path is corresponding at least one regulating command;
Unit is adjusted, the parameter of body-building equipment is adjusted for the regulating command according to corresponding to the target gesture path, it is described
Parameter includes speed and/or the gradient.
8. device according to claim 7, which is characterized in that described device further include:
Second acquisition unit, for obtaining the user information of the body builder, the user information includes age, gender and static state
Heart rate;
Computing unit, for calculating the default heart rate range according to the user information.
9. device according to claim 7, which is characterized in that described device further include:
Acquisition unit, for acquiring facial image to be identified, the facial image to be identified is the facial image of the body builder;
Second recognition unit, for identifying the facial image to be identified using preset human face recognition model, obtain it is described to
Identify the feature vector of facial image;
Second matching unit, for by multiple facial image samples in the feature vector and database of the facial image to be identified
This feature vector is matched, and obtains matching result, wherein user associated by the facial image sample sets with body-building
Standby access right;
Unit is activated, for judging whether the body builder has the right to use of the body-building equipment according to the matching result
Limit, if so, activating the body-building equipment.
10. a kind of body-building equipment, including the parameter regulation dress described in any one of claim 7~9 based on gesture identification
It sets.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811536853.1A CN109784178A (en) | 2018-12-14 | 2018-12-14 | Parameter adjusting method, device and body-building equipment based on gesture identification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811536853.1A CN109784178A (en) | 2018-12-14 | 2018-12-14 | Parameter adjusting method, device and body-building equipment based on gesture identification |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109784178A true CN109784178A (en) | 2019-05-21 |
Family
ID=66497009
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811536853.1A Pending CN109784178A (en) | 2018-12-14 | 2018-12-14 | Parameter adjusting method, device and body-building equipment based on gesture identification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109784178A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110215198A (en) * | 2019-06-03 | 2019-09-10 | Oppo广东移动通信有限公司 | Measurement of central venous pressure method and relevant apparatus |
CN111178308A (en) * | 2019-12-31 | 2020-05-19 | 北京奇艺世纪科技有限公司 | Gesture track recognition method and device |
CN112270302A (en) * | 2020-11-17 | 2021-01-26 | 支付宝(杭州)信息技术有限公司 | Limb control method and device and electronic equipment |
CN112807617A (en) * | 2021-02-22 | 2021-05-18 | 苏州进动智能科技有限公司 | Running safety monitoring and guiding method and equipment based on three-dimensional camera |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105357363A (en) * | 2015-09-24 | 2016-02-24 | 努比亚技术有限公司 | Wearable device based application starting method and device |
WO2017049817A1 (en) * | 2015-09-24 | 2017-03-30 | 北京零零无限科技有限公司 | Method and apparatus for operating unmanned aerial vehicle by means of gestures |
CN108596092A (en) * | 2018-04-24 | 2018-09-28 | 亮风台(上海)信息科技有限公司 | Gesture identification method, device, equipment and storage medium |
CN108921101A (en) * | 2018-07-04 | 2018-11-30 | 百度在线网络技术(北京)有限公司 | Processing method, equipment and readable storage medium storing program for executing based on gesture identification control instruction |
-
2018
- 2018-12-14 CN CN201811536853.1A patent/CN109784178A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105357363A (en) * | 2015-09-24 | 2016-02-24 | 努比亚技术有限公司 | Wearable device based application starting method and device |
WO2017049817A1 (en) * | 2015-09-24 | 2017-03-30 | 北京零零无限科技有限公司 | Method and apparatus for operating unmanned aerial vehicle by means of gestures |
CN108596092A (en) * | 2018-04-24 | 2018-09-28 | 亮风台(上海)信息科技有限公司 | Gesture identification method, device, equipment and storage medium |
CN108921101A (en) * | 2018-07-04 | 2018-11-30 | 百度在线网络技术(北京)有限公司 | Processing method, equipment and readable storage medium storing program for executing based on gesture identification control instruction |
Non-Patent Citations (1)
Title |
---|
王浩宇;漆晶;方天恩;刘德庆;: "基于轨迹模板匹配的动态手势识别方法", 单片机与嵌入式***应用, no. 07 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110215198A (en) * | 2019-06-03 | 2019-09-10 | Oppo广东移动通信有限公司 | Measurement of central venous pressure method and relevant apparatus |
CN110215198B (en) * | 2019-06-03 | 2022-04-29 | Oppo广东移动通信有限公司 | Central venous pressure measuring method and related device |
CN111178308A (en) * | 2019-12-31 | 2020-05-19 | 北京奇艺世纪科技有限公司 | Gesture track recognition method and device |
CN112270302A (en) * | 2020-11-17 | 2021-01-26 | 支付宝(杭州)信息技术有限公司 | Limb control method and device and electronic equipment |
CN112807617A (en) * | 2021-02-22 | 2021-05-18 | 苏州进动智能科技有限公司 | Running safety monitoring and guiding method and equipment based on three-dimensional camera |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109784178A (en) | Parameter adjusting method, device and body-building equipment based on gesture identification | |
US11380316B2 (en) | Speech interaction method and apparatus | |
WO2021051579A1 (en) | Body pose recognition method, system, and apparatus, and storage medium | |
Zhang et al. | Hand gesture recognition and virtual game control based on 3D accelerometer and EMG sensors | |
CN107798653B (en) | Image processing method and device | |
CN106096662B (en) | Human motion state identification based on acceleration transducer | |
CN108234870A (en) | Image processing method, device, terminal and storage medium | |
CN107257996A (en) | The method and system of environment sensitive automatic speech recognition | |
Jensen et al. | Classification of kinematic swimming data with emphasis on resource consumption | |
CN109841221A (en) | Parameter adjusting method, device and body-building equipment based on speech recognition | |
CN104036776A (en) | Speech emotion identification method applied to mobile terminal | |
CN110298220B (en) | Action video live broadcast method, system, electronic equipment and storage medium | |
CN109240786B (en) | Theme changing method and electronic equipment | |
CN107273857B (en) | Motion action recognition method and device and electronic equipment | |
CN109165555A (en) | Man-machine finger-guessing game method, apparatus and storage medium based on image recognition | |
CN110298218B (en) | Interactive fitness device and interactive fitness system | |
CN109621331A (en) | Fitness-assisting method, apparatus and storage medium, server | |
CN109448815A (en) | Self-service body building method, device, computer equipment and storage medium | |
CN111918122A (en) | Video processing method and device, electronic equipment and readable storage medium | |
CN110471529A (en) | Act methods of marking and device | |
CN110480656A (en) | One kind is accompanied and attended to robot, accompany and attend to robot control method and device | |
CN115331314A (en) | Exercise effect evaluation method and system based on APP screening function | |
CN109033448B (en) | Learning guidance method and family education equipment | |
CN109697676A (en) | Customer analysis and application method and device based on social group | |
CN112791367A (en) | Exercise assisting device and exercise assisting method |
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 | ||
AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20240712 |