CN111986260A - Image processing method and device and terminal equipment - Google Patents
Image processing method and device and terminal equipment Download PDFInfo
- Publication number
- CN111986260A CN111986260A CN202010921355.XA CN202010921355A CN111986260A CN 111986260 A CN111986260 A CN 111986260A CN 202010921355 A CN202010921355 A CN 202010921355A CN 111986260 A CN111986260 A CN 111986260A
- Authority
- CN
- China
- Prior art keywords
- action
- standard
- image
- limb
- skeleton image
- 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
- 238000003672 processing method Methods 0.000 title abstract description 11
- 230000009471 action Effects 0.000 claims abstract description 241
- 238000000034 method Methods 0.000 claims abstract description 30
- 238000010606 normalization Methods 0.000 claims description 62
- 230000000694 effects Effects 0.000 claims description 23
- 238000001514 detection method Methods 0.000 claims description 14
- 210000003414 extremity Anatomy 0.000 description 143
- 210000000707 wrist Anatomy 0.000 description 12
- 210000003423 ankle Anatomy 0.000 description 10
- 210000003127 knee Anatomy 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000033001 locomotion Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 5
- 230000036541 health Effects 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 210000002683 foot Anatomy 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/30—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
Abstract
The embodiment of the application discloses an image processing method, an image processing device and terminal equipment, wherein the method comprises the following steps: acquiring an image of the body-building action; detecting the position of an action limb point corresponding to the body-building action in the image; comparing the position of the action limb point with the position of the standard limb point corresponding to the body-building action to obtain a comparison result; and obtaining the standard degree of the body-building action according to the comparison result. The method comprises the steps that when a body builder makes body building actions according to a body building video, images of the body building actions of the body builder are collected, action limb points of the body builder in the images of the body building actions and standard limb points of the standard body building actions in the body building video are obtained, the action limb points and the standard limb points are compared, position deviation between the action limb points and the standard limb points is obtained, and whether the body building actions of the body builder are standard or not is reflected according to the deviation. Therefore, in the application, when the body builder performs body building according to the body building video, whether the body building action is standard or not can be known.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to an image processing method, an image processing apparatus, and a terminal device.
Background
With the popularization of the national fitness activities, people also begin to pay attention to the self health condition, and more people can perform the fitness activities.
At present, a body builder can learn various body building actions by watching a body building video to achieve the purpose of body building. When the body-building action is learned by watching the body-building video, the body-building person can complete the corresponding body-building action according to the demonstration of the body-building action in the body-building video and the voice indication of the body-building action.
However, the exerciser often cannot know whether the exercise action made by the exerciser meets the standard. The non-standard body-building action can not achieve the purpose of body building, but can also generate negative influence on the health condition.
Disclosure of Invention
In order to solve the technical problem, the application provides an image processing method, an image processing device and a terminal device, so that a body builder can know whether a body building action made by the body builder meets a standard or not.
The embodiment of the application discloses the following technical scheme:
in a first aspect, an embodiment of the present application provides an image processing method, including:
acquiring an image of the body-building action;
detecting the position of an action limb point corresponding to the fitness action in the image;
comparing the position of the action limb point with the position of a standard limb point corresponding to the body-building action to obtain a comparison result;
and obtaining the standard degree of the body-building action according to the comparison result.
Optionally, the comparing the position of the action limb point with the position of the standard limb point corresponding to the fitness action includes:
acquiring a skeleton image corresponding to the action limb point, and performing normalization processing on the skeleton image; acquiring a standard skeleton image corresponding to the standard limb point, and performing normalization processing on the standard skeleton image;
and comparing the position of the action limb point in the skeleton image after the normalization processing with the position of the standard limb point in the standard skeleton image after the normalization processing.
Optionally, comparing the position of the action limb point in the skeleton image after the normalization processing with the position of the standard limb point in the standard skeleton image after the normalization processing includes:
placing the normalized skeleton image and the normalized standard skeleton image in the same coordinate system, and enabling the position of the normalized skeleton image to coincide with the position of the normalized standard skeleton image;
in the coordinate system, comparing the action limb points in the skeleton image after the normalization processing with the standard limb points in the standard skeleton image after the normalization processing;
the obtaining of the comparison result comprises: and obtaining the distance between the action limb point in the skeleton image after the normalization processing and the standard limb point in the standard skeleton image after the normalization processing.
Optionally, the obtaining the standard degree of the exercise according to the comparison result includes:
obtaining the scores of the action limb points according to the distance; the distance is inversely related to the score of the action limb point;
and obtaining the total score of the body-building action according to the corresponding score proportion of the action limb point in the body-building action and the score of the limb point, and taking the total score as the standard degree.
Optionally, after obtaining the total score of the workout activities, the method further comprises:
displaying the total score in the image of the workout activity and/or in the image of a standard workout activity.
Optionally, after obtaining the total score of the workout activities, the method further comprises:
recording the fitness action of which the total score is smaller than a preset score threshold value, and generating feedback information;
displaying the feedback information in the image of the workout activity and/or in the image of a standard workout activity.
Optionally, the position of the standard limb point corresponding to the body-building action is obtained in real time or obtained in advance.
In a second aspect, an embodiment of the present application provides an apparatus for image processing, including: the device comprises an acquisition module, a detection module and a processing module;
the acquisition module is used for acquiring the image of the body-building action;
the detection module is used for detecting the position of an action limb point corresponding to the body-building action in the image;
the processing module is used for comparing the position of the action limb point with the position of a standard limb point corresponding to the body-building action to obtain a comparison result; and obtaining the standard degree of the body-building action according to the comparison result.
Optionally, the processing module is specifically configured to acquire a skeleton image corresponding to the action limb point, and perform normalization processing on the skeleton image; acquiring a standard skeleton image corresponding to the standard limb point, and performing normalization processing on the standard skeleton image; and comparing the position of the action limb point in the skeleton image after the normalization processing with the position of the standard limb point in the standard skeleton image after the normalization processing.
Optionally, the processing module is specifically configured to place the skeleton image after the normalization processing and the standard skeleton image after the normalization processing in the same coordinate system, so that the position of the skeleton image after the normalization processing coincides with the position of the standard skeleton image after the normalization processing; in the coordinate system, comparing the action limb points in the skeleton image after the normalization processing with the standard limb points in the standard skeleton image after the normalization processing; and the distance between the action limb point in the skeleton image after the normalization processing and the standard limb point in the standard skeleton image after the normalization processing is obtained.
Optionally, the processing module is specifically configured to obtain the score of the action limb point according to the distance; the distance is inversely related to the score of the action limb point; and obtaining the total score of the body-building action according to the corresponding score proportion of the action limb point in the body-building action and the score of the limb point, and taking the total score as the standard degree.
Optionally, the processing module is further configured to display the total score in the image of the exercise motion and/or the image of the standard exercise motion after obtaining the total score of the exercise motion.
Optionally, the processing module is further configured to record the fitness action with the total score smaller than a preset score threshold after obtaining the total score of the fitness action, and generate feedback information; displaying the feedback information in the image of the workout activity and/or in the image of a standard workout activity.
In a third aspect, an embodiment of the present application provides a terminal device, including the apparatus in any one of the second aspects.
According to the technical scheme, the embodiment of the application has the following advantages:
the application provides an image processing method, an image processing device and terminal equipment, wherein the method comprises the following steps: acquiring an image of the body-building action; detecting the position of an action limb point corresponding to the fitness action in the image; comparing the position of the action limb point with the position of a standard limb point corresponding to the body-building action to obtain a comparison result; and obtaining the standard degree of the body-building action according to the comparison result. The method comprises the steps that when a body builder makes body building actions according to a body building video, images of the body building actions of the body builder are collected, action limb points of the body builder in the images of the body building actions and standard limb points of the standard body building actions in the body building video are obtained, the action limb points and the standard limb points are compared, position deviation between the action limb points and the standard limb points is obtained, and whether the body building actions of the body builder are standard or not is reflected according to the deviation. Therefore, in the application, when the body builder performs body building according to the body building video, whether the body building action is standard or not can be known.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of an image processing method according to an embodiment of the present disclosure;
fig. 2 is a schematic diagram of an image acquisition provided by an embodiment of the present application;
fig. 3 is a schematic diagram of a skeleton image according to an embodiment of the present disclosure;
FIG. 4 is a diagram of a standard skeleton image according to an embodiment of the present disclosure;
FIG. 5 is a schematic diagram of a skeleton image contrast provided by an embodiment of the present application;
fig. 6 is a schematic diagram of an image processing apparatus according to an embodiment of the present application.
Detailed Description
The body builder can learn various body building actions through the body building video recording so as to achieve the purpose of body building. However, when a user performs a fitness operation by watching the fitness video, the user cannot know whether the fitness operation is standard or not after the user performs the fitness operation although the user can know how the fitness operation should be performed. However, non-standard exercise activities do not achieve the goal of exercise and can also have negative effects on the health of the body.
In order to solve the above problem, the present application provides an image processing method, an image processing apparatus, and a terminal device. By adopting the method, when the body builder performs corresponding body building actions according to the body building video, the body building action images of the body builder are collected and displayed in a preset area, such as: projected onto a wall surface or displayed in a display. Therefore, the body builder can also see the body building action made by the body builder when watching the body building video. After the body-building action of the body-building person is collected, the position of an action limb point in the body-building action is detected through a pre-established human body key point detection model, the position of the action limb point is compared with the position of a standard limb point corresponding to the body-building action, so that the standard degree of the body-building action of the body-building person is obtained, and then the standard degree is displayed in a preset area. Therefore, by adopting the technical scheme of the application, a body builder can know whether the body building action is standard or not when performing body building according to the body building video.
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The first embodiment is as follows:
the embodiment of the present application provides an image processing method, which is described in detail below with reference to the accompanying drawings.
Referring to fig. 1, the flowchart of a method for processing an image according to an embodiment of the present application is shown.
The method can be used for terminal equipment, the type of the terminal equipment is not limited in the application, and the terminal equipment can be a mobile phone, a touch projection equipment and other terminal equipment with functions of displaying images and recording images. The method comprises the following steps:
step 101: an image of the fitness activity is obtained.
In order to judge whether the fitness action of the builder is standard, the image of the fitness action needs to be acquired when the builder performs the fitness action according to the fitness video.
The method for acquiring the image of the body-building action is not limited in the application, and the image may be acquired by an image acquisition device built in the terminal device, for example, a camera.
When the body builder makes body building actions according to the body building video, the camera simultaneously acquires the body building actions of the body builder.
Referring to fig. 2, the figure is a schematic diagram of image acquisition according to an embodiment of the present application.
When a body builder is about to start body building, the terminal equipment prompts the body builder to enter an effective identification area through a built-in loudspeaker, the body builder is identified firstly, after identification is successful, the terminal equipment shoots the body building action image of the body builder through built-in image acquisition equipment, meanwhile, a body building video record starts to be played, and the body builder can make body building actions according to the body building video record.
Step 102: and detecting the position of the action limb point corresponding to the body-building action in the image.
The positions of the action limb points corresponding to the body-building action can be obtained through a pre-established human body key point detection model. The following describes the establishment of the human body key point detection model in detail.
And acquiring training data and a training result, wherein the training data is an image of historical fitness movement, and the training result is an image of the historical fitness movement with the position of the movement limb point marked.
Training the training data and the training result through a Convolutional Neural Network (CNN) model to obtain a human body key point detection model.
Therefore, based on the pre-established human key point detection model, the action limb points in the image of the fitness action can be identified. Wherein the action limb points comprise a plurality of left shoulder, right shoulder, left elbow, right elbow, left wrist, right wrist, left hip, right hip, left leg knee, right leg knee, left ankle, right ankle, and nose.
Step 103: and comparing the position of the action limb point with the position of the standard limb point corresponding to the body-building action to obtain a comparison result.
And after the position of the action limb point and the position of the standard limb point are obtained, comparing the two positions, and determining a comparison result.
The standard limb point can be obtained in real time according to the fitness video when the exerciser does the fitness action, or can be obtained in advance according to the fitness video. The process of obtaining the standard limb points is similar to the process of obtaining the action limb points in the step 102, that is, the standard limb points of the fitness action in the fitness video are obtained through the human body key point detection model. Therefore, the standard limb points and the action limb points are obtained through the same human body key point detection model, and the errors obtained through different modes are reduced by adopting the same obtaining mode.
In addition, in order to reduce the operating pressure of the processor, the standard limb points of the fitness actions in the fitness video record can be calibrated in advance in an artificial calibration mode.
The process of comparing the position of the action limb point with the position of the standard limb point corresponding to the fitness action is described in detail below with reference to fig. 3.
Referring to fig. 3, the figure is a schematic view of a skeleton image provided in an embodiment of the present application.
And acquiring a skeleton image corresponding to the action limb point according to the acquired position of the action limb point. Specifically, a left ankle 301, a left knee 302, a left hip 303, a left shoulder 304, a right shoulder 305, a right hip 306, a right knee 307, and a right ankle 308 are connected, a left wrist 309, a left elbow 310, and a left shoulder 304 are connected, and a right wrist 311, a right elbow 312, and a right shoulder 305 are connected.
Referring to fig. 4, the figure is a schematic diagram of a standard skeleton image according to an embodiment of the present application.
The fitness action shown by the standard skeleton image is the same as the fitness action shown by the skeleton image, and the standard degree of the fitness action of the fitness person can be judged according to the difference of the skeletons because the skeletons are different.
And acquiring a skeleton image corresponding to the standard limb point according to the position of the acquired standard limb point. Specifically, a left ankle 401, a left knee 402, a left hip 403, a left shoulder 404, a right shoulder 405, a right hip 406, a right knee 407, and a right ankle 408 are connected, a left wrist 409, a left elbow 410, and a left shoulder 404 are connected, and a right wrist 411, a right elbow 412, and a right shoulder 405 are connected.
After obtaining the skeleton image, normalization processing needs to be performed on the skeleton image. Specifically, a rectangular coordinate system is established with the lower left corner of the skeleton image as the origin, and the maximum value and the minimum value of the vertical coordinate of the action limb point in the skeleton image are obtained, for example: in fig. 3, the ordinate of the nose 313 is the maximum value, the ordinate of the left ankle 301 is the minimum value, and the difference value between the ordinate of the nose 313 and the ordinate of the left ankle 301 is taken as the height of the skeleton image; in fig. 3, the abscissa of the left wrist 309 is the minimum value, the abscissa of the right elbow 312 is the maximum value, and the difference between the abscissa of the left wrist 309 and the ordinate of the right elbow 312 is taken as the width of the skeleton image, and therefore, the ratio of the width to the height of the skeleton image can be obtained.
After the skeleton image is scaled, the ratio of the width to the height of the skeleton image is consistent with a preset ratio, and the preset ratio may be the ratio of the width to the height of the standard skeleton image, or may be other ratios, for example: the preset 1 ratio is 1 × 1.
Similarly, a standard skeleton image corresponding to the standard limb point can be obtained, and the standard skeleton image is normalized. The normalization process for the standard skeleton image may be performed in advance, or may be performed simultaneously with the normalization process for the skeleton image.
After normalization processing, the positions of the action limb points in the skeleton image after normalization processing and the positions of the standard limb points in the standard skeleton image after normalization processing can be respectively obtained; then, the position of the action limb point in the skeleton image after the normalization processing is compared with the position of the standard limb point in the standard skeleton image after the normalization processing.
Specifically, the skeleton image after normalization processing and the standard skeleton image after normalization processing are placed in the same coordinate system, so that the position of the skeleton image after normalization processing is superposed with the position of the standard skeleton image after normalization processing; and in the coordinate system, comparing the action limb points in the skeleton image after the normalization processing with the standard limb points in the standard skeleton image after the normalization processing. Because the skeleton image and the standard skeleton image are located in the same coordinate system, the distance between the action limb point in the skeleton image after the normalization processing and the standard limb point in the standard skeleton image after the normalization processing can be obtained according to the coordinate of the action limb point and the coordinate of the standard limb point.
Referring to fig. 5, the figure is a schematic diagram of a skeleton image contrast provided in an embodiment of the present application.
Wherein, the skeleton connected by the dotted line is the skeleton image corresponding to the body-building action made by the body-building person, and the skeleton connected by the solid line is the standard skeleton image corresponding to the standard body-building action. For example: since the coordinates of the left leg knee 303 of the action limb point are (30,30) and the coordinates of the left leg knee 402 of the standard limb point are (50,20), the distance between the position of the left leg knee 302 of the action limb point and the position of the left leg knee 402 of the standard limb point can be obtained from the coordinates of the two points.
Similarly, the distance between the position of the left ankle of the action limb point and the position of the left ankle of the standard limb point can also be acquired, and therefore, the distance between the position of each action limb point and the position of each standard limb point can be acquired.
Step 104: and obtaining the standard degree of the body-building action according to the comparison result.
After obtaining the distance between the position of each action limb point and the position of each standard limb point, a comparison result may be generated, and the comparison result includes information of the distance between the position of each action limb point and the position of each standard limb point.
Obtaining the scores of the action limb points according to the distance; the distance is inversely related to the score of the action limb point; the greater the deviation of the position of the action limb point from the position of the standard limb point, the greater the distance between the position of the action limb point and the position of the standard limb point. For example, the greater the deviation of the left wrist in the workout from the left wrist of the standard workout, the less standard the left wrist of the workout, and therefore the lower the score for the left wrist of the workout.
Because different action limb points have different influences on the standard degree of the body-building action, for example, the influence of the nose on the standard degree of the body-building action is low, and the influence of the left shoulder on the marking degree of the body-building action is large, the fraction proportion of the nose in the body-building action is reduced, and the fraction proportion of the left shoulder in the body-building action is improved. The fraction ratio can be preset, and can also be adjusted correspondingly according to different habits of the body builder.
And obtaining the total score of the body-building action according to the corresponding score proportion of the action limb point in the body-building action and the score of the limb point, and taking the total score as the standard degree.
After the score of each action limb point and the score proportion of the action limb point are obtained, the total score of the fitness action can be calculated, and the standard degree of the fitness action is embodied through the total score.
In addition, the exercise motions with the total score lower than the preset score threshold can be set as nonstandard by setting the preset score threshold, and the exercise motions with the total score higher than the preset score threshold are set as standard.
In order to enable the body-building person to know the body-building action deficiency of the body-building person, the body-building action with the total score smaller than a preset score threshold value can be recorded, and feedback information is generated; the feedback information may be voice information, for example, playing "please raise the left foot", or text information, or information combining voice and text.
When the feedback information comprises the text information, the feedback information can be displayed on the image of the body-building action, and also can be displayed on the body-building video record, so that the body-building person can observe the defects of the body-building person when doing the body-building action.
Besides displaying the feedback information, the total score can be displayed on the image of the fitness action, and the total score can also be displayed on the fitness video.
After the exerciser observes the total score of the exercise actions performed by the exerciser, the exerciser can know the deficiency of the exerciser.
The image processing method provided by the application comprises the following steps: acquiring an image of the body-building action; detecting the position of an action limb point corresponding to the fitness action in the image; comparing the position of the action limb point with the position of a standard limb point corresponding to the body-building action to obtain a comparison result; and obtaining the standard degree of the body-building action according to the comparison result. The method comprises the steps that when a body builder makes body building actions according to a body building video, images of the body building actions of the body builder are collected, action limb points of the body builder in the images of the body building actions and standard limb points of the standard body building actions in the body building video are obtained, the action limb points and the standard limb points are compared, position deviation between the action limb points and the standard limb points is obtained, and whether the body building actions of the body builder are standard or not is reflected according to the deviation. Therefore, in the application, when the body builder performs body building according to the body building video, whether the body building action is standard or not can be known.
Example two:
the second embodiment of the present application provides an image processing apparatus, which is described in detail below with reference to the accompanying drawings.
Referring to fig. 6, this figure is a schematic diagram of an apparatus for image processing according to an embodiment of the present application.
The image processing apparatus includes: an acquisition module 601, a detection module 602, and a processing module 603.
The obtaining module 601 is configured to obtain an image of a fitness action.
The detecting module 602 is configured to detect a position of an action limb point corresponding to the exercise action in the image.
The processing module 603 is configured to compare the position of the action limb point with the position of the standard limb point corresponding to the fitness action, and obtain a comparison result; and obtaining the standard degree of the body-building action according to the comparison result.
As a possible implementation manner, the processing module 603 is specifically configured to acquire a skeleton image corresponding to the action limb point, and perform normalization processing on the skeleton image; acquiring a standard skeleton image corresponding to the standard limb point, and performing normalization processing on the standard skeleton image; and comparing the position of the action limb point in the skeleton image after the normalization processing with the position of the standard limb point in the standard skeleton image after the normalization processing.
As a possible implementation manner, the processing module 603 is specifically configured to place the normalized skeleton image and the normalized standard skeleton image in the same coordinate system, so that the position of the normalized skeleton image coincides with the position of the normalized standard skeleton image; in the coordinate system, comparing the action limb points in the skeleton image after the normalization processing with the standard limb points in the standard skeleton image after the normalization processing; and the distance between the action limb point in the skeleton image after the normalization processing and the standard limb point in the standard skeleton image after the normalization processing is obtained.
As a possible implementation manner, the processing module 603 is specifically configured to obtain a score of the action limb point according to the distance; the distance is inversely related to the score of the action limb point; and obtaining the total score of the body-building action according to the corresponding score proportion of the action limb point in the body-building action and the score of the limb point, and taking the total score as the standard degree.
As a possible implementation, the processing module 603 is further configured to display the total score in the image of the fitness action and/or the image of the standard fitness action after obtaining the total score of the fitness action.
As a possible implementation manner, the processing module is further configured to, after obtaining the total score of the fitness activities, record the fitness activities of which the total score is smaller than a preset score threshold, and generate feedback information; displaying the feedback information in the image of the workout activity and/or in the image of a standard workout activity.
The image processing apparatus provided by the present application includes: the device comprises an acquisition module, a detection module and a processing module; the acquisition module is used for acquiring the image of the body-building action; the detection module is used for detecting the position of an action limb point corresponding to the body-building action in the image; the processing module is used for comparing the position of the action limb point with the position of a standard limb point corresponding to the body-building action to obtain a comparison result; and obtaining the standard degree of the body-building action according to the comparison result. The method comprises the steps that when a body builder makes body building actions according to a body building video, images of the body building actions of the body builder are collected, action limb points of the body builder in the images of the body building actions and standard limb points of the standard body building actions in the body building video are obtained, the action limb points and the standard limb points are compared, position deviation between the action limb points and the standard limb points is obtained, and whether the body building actions of the body builder are standard or not is reflected according to the deviation. Therefore, in the application, when the body builder performs body building according to the body building video, whether the body building action is standard or not can be known.
Example three:
the third embodiment of the application provides terminal equipment, the terminal equipment comprises any one of the devices introduced above, the terminal equipment can be a touch projection device, the terminal equipment can shoot images in a projection mode, and the terminal equipment comprises the device introduced above, so that when a body builder makes body building actions according to a body building video record, the terminal equipment collects the images of the body building actions of the body builder, obtains action limb points of the body builder in the images of the body building actions and obtains standard limb points of the standard body building actions in the body building video record, compares the action limb points with the standard limb points, obtains position deviation between the action limb points and the standard limb points, and reflects whether the body building actions of the body builder are standard or not according to the deviation. Therefore, in the application, when the body builder performs body building according to the body building video, whether the body building action is standard or not can be known.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium may be at least one of the following media: various media that can store program codes, such as read-only memory (ROM), RAM, magnetic disk, or optical disk.
It should be noted that, in the present specification, all the embodiments are described in a progressive manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the apparatus and system embodiments, since they are substantially similar to the method embodiments, they are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for related points. The above-described embodiments of the apparatus and system are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only one specific embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present application should be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A method of image processing, comprising:
acquiring an image of the body-building action;
detecting the position of an action limb point corresponding to the fitness action in the image;
comparing the position of the action limb point with the position of a standard limb point corresponding to the body-building action to obtain a comparison result;
and obtaining the standard degree of the body-building action according to the comparison result.
2. The method of claim 1, wherein comparing the location of the action limb point to the location of a standard limb point corresponding to the workout action comprises:
acquiring a skeleton image corresponding to the action limb point, and performing normalization processing on the skeleton image; acquiring a standard skeleton image corresponding to the standard limb point, and performing normalization processing on the standard skeleton image;
and comparing the position of the action limb point in the skeleton image after the normalization processing with the position of the standard limb point in the standard skeleton image after the normalization processing.
3. The method of claim 2, wherein comparing the position of the action limb point in the normalized skeleton image with the position of the standard limb point in the normalized standard skeleton image comprises:
placing the normalized skeleton image and the normalized standard skeleton image in the same coordinate system, and enabling the position of the normalized skeleton image to coincide with the position of the normalized standard skeleton image;
in the coordinate system, comparing the action limb points in the skeleton image after the normalization processing with the standard limb points in the standard skeleton image after the normalization processing;
the obtaining of the comparison result comprises: and obtaining the distance between the action limb point in the skeleton image after the normalization processing and the standard limb point in the standard skeleton image after the normalization processing.
4. The method of claim 3, wherein the obtaining the fitness action criteria from the comparison comprises:
obtaining the scores of the action limb points according to the distance; the distance is inversely related to the score of the action limb point;
and obtaining the total score of the body-building action according to the corresponding score proportion of the action limb point in the body-building action and the score of the limb point, and taking the total score as the standard degree.
5. The method of claim 4, wherein after obtaining the total score for the workout activity, the method further comprises:
displaying the total score in the image of the workout activity and/or in the image of a standard workout activity.
6. The method of claim 4, wherein after obtaining the total score for the workout activity, the method further comprises:
recording the fitness action of which the total score is smaller than a preset score threshold value, and generating feedback information;
displaying the feedback information in the image of the workout activity and/or in the image of a standard workout activity.
7. An apparatus for image processing, comprising: the device comprises an acquisition module, a detection module and a processing module;
the acquisition module is used for acquiring the image of the body-building action;
the detection module is used for detecting the position of an action limb point corresponding to the body-building action in the image;
the processing module is used for comparing the position of the action limb point with the position of a standard limb point corresponding to the body-building action to obtain a comparison result; and obtaining the standard degree of the body-building action according to the comparison result.
8. The device according to claim 7, wherein the processing module is specifically configured to acquire a skeleton image corresponding to the action limb point, and perform normalization processing on the skeleton image; acquiring a standard skeleton image corresponding to the standard limb point, and performing normalization processing on the standard skeleton image; and comparing the position of the action limb point in the skeleton image after the normalization processing with the position of the standard limb point in the standard skeleton image after the normalization processing.
9. The apparatus according to claim 8, wherein the processing module is specifically configured to place the normalized skeleton image and the normalized standard skeleton image in a same coordinate system, so that a position of the normalized skeleton image coincides with a position of the normalized standard skeleton image; in the coordinate system, comparing the action limb points in the skeleton image after the normalization processing with the standard limb points in the standard skeleton image after the normalization processing; and the distance between the action limb point in the skeleton image after the normalization processing and the standard limb point in the standard skeleton image after the normalization processing is obtained.
10. A terminal device, characterized in that it comprises the apparatus of any of claims 7-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010921355.XA CN111986260A (en) | 2020-09-04 | 2020-09-04 | Image processing method and device and terminal equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010921355.XA CN111986260A (en) | 2020-09-04 | 2020-09-04 | Image processing method and device and terminal equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111986260A true CN111986260A (en) | 2020-11-24 |
Family
ID=73447552
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010921355.XA Pending CN111986260A (en) | 2020-09-04 | 2020-09-04 | Image processing method and device and terminal equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111986260A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108471986A (en) * | 2016-01-21 | 2018-08-31 | 普莱西公司 | For using the perimeter of body part to change the devices, systems, and methods of progress health monitoring |
| CN108734104A (en) * | 2018-04-20 | 2018-11-02 | 杭州易舞科技有限公司 | Body-building action error correction method based on deep learning image recognition and system |
| CN109472269A (en) * | 2018-10-17 | 2019-03-15 | 深圳壹账通智能科技有限公司 | Characteristics of image configuration and method of calibration, device, computer equipment and medium |
| CN109829442A (en) * | 2019-02-22 | 2019-05-31 | 焦点科技股份有限公司 | A kind of method and system of the human action scoring based on camera |
| CN109948459A (en) * | 2019-02-25 | 2019-06-28 | 广东工业大学 | A kind of football movement appraisal procedure and system based on deep learning |
| CN111488824A (en) * | 2020-04-09 | 2020-08-04 | 北京百度网讯科技有限公司 | Motion prompting method and device, electronic equipment and storage medium |
| CN111563487A (en) * | 2020-07-14 | 2020-08-21 | 平安国际智慧城市科技股份有限公司 | Dance scoring method based on gesture recognition model and related equipment |
-
2020
- 2020-09-04 CN CN202010921355.XA patent/CN111986260A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108471986A (en) * | 2016-01-21 | 2018-08-31 | 普莱西公司 | For using the perimeter of body part to change the devices, systems, and methods of progress health monitoring |
| CN108734104A (en) * | 2018-04-20 | 2018-11-02 | 杭州易舞科技有限公司 | Body-building action error correction method based on deep learning image recognition and system |
| CN109472269A (en) * | 2018-10-17 | 2019-03-15 | 深圳壹账通智能科技有限公司 | Characteristics of image configuration and method of calibration, device, computer equipment and medium |
| CN109829442A (en) * | 2019-02-22 | 2019-05-31 | 焦点科技股份有限公司 | A kind of method and system of the human action scoring based on camera |
| CN109948459A (en) * | 2019-02-25 | 2019-06-28 | 广东工业大学 | A kind of football movement appraisal procedure and system based on deep learning |
| CN111488824A (en) * | 2020-04-09 | 2020-08-04 | 北京百度网讯科技有限公司 | Motion prompting method and device, electronic equipment and storage medium |
| CN111563487A (en) * | 2020-07-14 | 2020-08-21 | 平安国际智慧城市科技股份有限公司 | Dance scoring method based on gesture recognition model and related equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230338778A1 (en) | Method and system for monitoring and feed-backing on execution of physical exercise routines | |
| US8907982B2 (en) | Mobile device for augmented reality applications | |
| US9154739B1 (en) | Physical training assistant system | |
| CN110428486B (en) | Virtual interaction fitness method, electronic equipment and storage medium | |
| CN110298220B (en) | Action video live broadcast method, system, electronic equipment and storage medium | |
| CN112464918A (en) | Body-building action correcting method and device, computer equipment and storage medium | |
| EP3786971A1 (en) | Advancement manager in a handheld user device | |
| CN112734799A (en) | Body-building posture guidance system | |
| KR102356685B1 (en) | Home training providing system based on online group and method thereof | |
| CN113409651B (en) | Live broadcast body building method, system, electronic equipment and storage medium | |
| CN115569344A (en) | Standing long jump score evaluation method and device, electronic equipment and storage medium | |
| CN111680538A (en) | Method and device for identifying stability of memorial meditation | |
| CN113262459B (en) | Method, apparatus and medium for determining motion standard of sport body-building mirror | |
| CN111986260A (en) | Image processing method and device and terminal equipment | |
| CN116152924A (en) | Motion gesture evaluation method, device and system and computer storage medium | |
| CN114241604A (en) | Gesture detection method and device, electronic equipment and storage medium | |
| KR101892514B1 (en) | Automatic score calculation system for billiard game using coordinate values | |
| Li et al. | Fitness coach: Design and implementation of a smart mirror based on automatic image recognition and action model comparison | |
| CN113842622B (en) | Motion teaching method, device, system, electronic equipment and storage medium | |
| CN116153510B (en) | Correction mirror control method, device, equipment, storage medium and intelligent correction mirror | |
| CN116071814A (en) | Gesture monitoring method and device, electronic equipment, computer readable medium and product | |
| CN116935484A (en) | Counting method, device, equipment and medium for deep squat jumping | |
| CN117095457A (en) | Digital person reconstruction motion scoring method, system, equipment and medium | |
| CN115331305A (en) | Open-close jump counting method, device, equipment and medium based on human body key points | |
| CN116486299A (en) | Motion quantity statistical method, device and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |