CN113935921A - Mirror-surface type fitness information interaction method and system - Google Patents
Mirror-surface type fitness information interaction method and system Download PDFInfo
- Publication number
- CN113935921A CN113935921A CN202111216065.6A CN202111216065A CN113935921A CN 113935921 A CN113935921 A CN 113935921A CN 202111216065 A CN202111216065 A CN 202111216065A CN 113935921 A CN113935921 A CN 113935921A
- Authority
- CN
- China
- Prior art keywords
- image data
- data
- image
- user
- coordinate data
- 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 26
- 230000003993 interaction Effects 0.000 title claims abstract description 24
- 230000009471 action Effects 0.000 claims abstract description 25
- 239000000284 extract Substances 0.000 claims description 18
- 230000002452 interceptive effect Effects 0.000 claims 1
- 230000033001 locomotion Effects 0.000 abstract description 5
- 230000008569 process Effects 0.000 abstract description 5
- 238000012544 monitoring process Methods 0.000 abstract description 4
- 230000036544 posture Effects 0.000 description 17
- 230000004048 modification Effects 0.000 description 8
- 238000012986 modification Methods 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000012937 correction Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 210000000689 upper leg Anatomy 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000002715 modification method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G06T5/77—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/403—Edge-driven scaling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- 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
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/74—Determining position or orientation of objects or cameras using feature-based methods involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20124—Active shape model [ASM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20132—Image cropping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
Abstract
The invention discloses a mirror-surface type body-building information interaction method, which comprises the following steps: acquiring a fitness video stream as first image data, and acquiring an image reflected by a mirror surface of a user as second image data; correcting the first image data according to the second image data until the first image data meets a preset condition; the preset condition is that the physical size of the coach in the corrected first image data corresponds to the physical size of the user in the second image data; displaying the corrected first image data on the mirror surface and overlapping the reflected image on the mirror surface; the movement of the coach in the modified first image data is the same as the movement of the user in the reflected image, and the shape of the coach in the modified first image data is coincident with the shape of the user in the reflected image. The mirror-surface type body-building information interaction method and system provided by the invention realize the real-time monitoring of the body-building action and the standard action difference of a body-building person in the body-building process, effectively improve the body-building efficiency and also improve the use experience of the body-building person.
Description
Technical Field
The invention relates to fitness information data processing, in particular to a mirror-surface type fitness information interaction method and system.
Background
Fitness is a sport, such as various freehand aerobics, rhythm exercises, gymnastics and various self-resistance movements, gymnastics and yoga, which can enhance strength and flexibility, increase endurance, improve coordination and control the ability of each part of the body, thereby making the body strong.
In the prior art, various home fitness equipment exists, wherein the fitness equipment capable of directly displaying a fitness coach video is more and more extensive, but the fitness equipment is difficult for a fitness person to accurately judge the accuracy of self fitness exercise.
Disclosure of Invention
The invention aims to solve the technical problem that fitness equipment in the prior art cannot enable a fitness person to accurately judge the accuracy of self fitness movement, and aims to provide a mirror-surface type fitness information interaction method and system to solve the problem.
The invention is realized by the following technical scheme:
in one aspect, a mirror-surface type fitness information interaction method is disclosed, which comprises the following steps:
acquiring a fitness video stream as first image data, and acquiring an image reflected by a mirror surface of a user as second image data;
correcting the first image data according to the second image data until a preset condition is met; the preset condition is that the physical size of the coach in the corrected first image data corresponds to the physical size of the user in the second image data;
displaying the corrected first image data at the mirror surface and overlapping the reflected image on the mirror surface; the action of the coach in the modified first image data is the same as the action of the user in the reflected image, and the shape of the coach in the modified first image data is superposed with the shape of the user in the reflected image.
In the prior art, the action condition of a body builder is scored mainly by wearing a sensor or video detection for the accuracy of the body building of the body builder, but the scoring result can only display whether the action of the body builder reaches the standard, but the body builder cannot intuitively know which part of the action does not reach the standard.
In this embodiment, when the user requests the fitness video stream by a selection request or a timed play, and the received fitness video stream is used as the first image data, it should be understood that the fitness video stream may be acquired by any existing method, such as data transmission based on the internet, short-distance data transmission, and pre-storage, and this embodiment is not limited in this respect.
The recording mode of the video in the first image data is often different from the reflection image obtained by the user in front of the mirror surface, for example, when the first image data is recorded, the shape of a coach may be different from the user, and when the user exercises, if the first image data is directly displayed, it is difficult to compare the action posture no matter how the user adjusts the position in front of the mirror surface. The image reflected by the mirror surface of the user is also acquired as the second image data in the present embodiment to correct the first image data.
In this embodiment, the first image data needs to be corrected according to the second image data by a device capable of performing calculation, and the result of the correction needs to satisfy that the physical size of the trainer in the first image data substantially matches the physical size of the user in the second image data. Through the technology, the invention realizes the real-time monitoring of the difference between the body-building action and the standard action of the body-building person in the body-building process, effectively improves the body-building efficiency and also improves the use experience of the body-building person.
Further, the correcting the first image data according to the second image data to satisfy a preset condition includes:
extracting coordinate data of the characteristic points from the first image data to form first coordinate data, and extracting coordinate data of the corresponding characteristic points from the second image data to form second coordinate data;
and correcting each frame in the first image data according to the difference between the second coordinate data and the first coordinate data until a preset condition is met.
Further, extracting the coordinate data of the feature point from the first image data to form first coordinate data, and extracting the coordinate data of the corresponding feature point from the second image data to form second coordinate data includes:
selecting a frame of which the coach reaches a preset posture from first image data as a first key frame, and extracting the outline of a coach preset part in the first key frame;
selecting a frame of which the user achieves the same preset posture from second image data as a second key frame, and extracting the outline of the same preset part of the user in the second key frame;
and extracting feature points based on the first keyframe corresponding contour and generating first coordinate data, and extracting feature points based on the second keyframe corresponding contour and generating second coordinate data.
Further, extracting feature points based on the contour includes:
extracting at least three points in the contour as the feature points, wherein the feature points are inflection points in the contour;
the feature points extracted based on the first keyframe correspond to the feature points extracted based on the second keyframe.
Further, the correcting each frame in the first image data according to the difference between the second coordinate data and the first coordinate data to satisfy a preset condition includes:
forming user body size data based on the second coordinate data and forming coach body size data based on the first coordinate data;
cropping and/or scaling each frame in the first image data in at least one direction according to a ratio of the user physique size data to the coach physique size data in that direction.
In one aspect, a mirror-type fitness information interaction system is disclosed, comprising:
a processor configured to obtain a fitness video stream as first image data;
a mirror configured to reflect an image of a user;
a camera configured to acquire an image reflected by a user at the mirror surface as second image data;
a display disposed below the mirror surface;
the processor corrects the first image data according to the second image data until a preset condition is met; the preset condition is that the physical size of the coach in the corrected first image data corresponds to the physical size of the user in the second image data;
the display displays the corrected first image data and is overlapped on the reflection image on the mirror surface; and when the action of the coach in the corrected first image data is the same as the action of the user in the reflected image, the shape of the coach in the image displayed by the display is superposed with the shape of the user in the reflected image.
Further, the processor is further configured to modify the first image data according to the second image data to satisfy a preset condition, including:
the processor extracts coordinate data of the characteristic points from the first image data to form first coordinate data, and extracts coordinate data of the corresponding characteristic points from the second image data to form second coordinate data;
and the processor corrects each frame in the first image data according to the difference between the second coordinate data and the first coordinate data until a preset condition is met.
Further, the processor is further configured to select a frame, in which the coach reaches a preset posture, from the first image data as a first key frame, and extract a contour of a coach preset part in the first key frame;
the processor selects frames of which the users reach the same preset posture from the second image data as second key frames, and extracts the outlines of the same preset parts of the users in the second key frames;
the processor extracts feature points based on the first keyframe corresponding contours and generates first coordinate data, and extracts feature points based on the second keyframe corresponding contours and generates second coordinate data.
Further, the processor is further configured to extract at least three points in the contour as the feature points, wherein the feature points are inflection points in the contour;
the feature points extracted by the processor based on the first keyframe correspond to feature points extracted based on the second keyframe.
Further, the processor is further configured to form user physique size data based on the second coordinate data and coach physique size data based on the first coordinate data;
the processor cropping and/or scaling each frame in the first image data in at least one direction according to a ratio of the user physical size data to the coach physical size data in that direction.
Compared with the prior art, the invention has the following advantages and beneficial effects:
the mirror-surface type body-building information interaction method and system provided by the invention realize the real-time monitoring of the body-building action and the standard action difference of a body-building person in the body-building process, effectively improve the body-building efficiency and also improve the use experience of the body-building person.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
FIG. 1 is a schematic illustration of the steps of an embodiment of the present invention;
FIG. 2 is a system architecture diagram according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating operation of a mirror and display in accordance with an embodiment of the present invention;
FIG. 4 is a schematic diagram of the mirror and the display after modification according to the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to examples and accompanying drawings, and the exemplary embodiments and descriptions thereof are only used for explaining the present invention and are not meant to limit the present invention.
Examples
Referring to fig. 1, a schematic flow chart of a mirror-type fitness information interaction method according to an embodiment of the present invention is shown, where the mirror-type fitness information interaction method can be applied to the mirror-type fitness information interaction system shown in fig. 2, and further, the mirror-type fitness information interaction method specifically includes the following steps S1-S3.
S1: acquiring a fitness video stream as first image data, and acquiring an image reflected by a mirror surface of a user as second image data;
s2: correcting the first image data according to the second image data until a preset condition is met; the preset condition is that the physical size of the coach in the corrected first image data corresponds to the physical size of the user in the second image data;
s3: displaying the corrected first image data at the mirror surface and overlapping the reflected image on the mirror surface; the action of the coach in the modified first image data is the same as the action of the user in the reflected image, and the shape of the coach in the modified first image data is superposed with the shape of the user in the reflected image.
In this embodiment, when the user requests the fitness video stream by a selection request or a timed play, and the received fitness video stream is used as the first image data, it should be understood that the fitness video stream may be acquired by any existing method, such as data transmission based on the internet, short-distance data transmission, and pre-storage, and this embodiment is not limited in this respect.
The recording mode of the video in the first image data is often different from the reflection image obtained by the user in front of the mirror surface, for example, when the first image data is recorded, the shape of a coach may be different from the user, and when the user exercises, if the first image data is directly displayed, it is difficult to compare the action posture no matter how the user adjusts the position in front of the mirror surface. The image reflected by the mirror surface of the user is also acquired as the second image data in the present embodiment to correct the first image data.
In this embodiment, the first image data needs to be corrected according to the second image data by a device capable of performing calculation, and the result of the correction needs to satisfy that the physical size of the trainer in the first image data substantially matches the physical size of the user in the second image data. Through the technology, the invention realizes the real-time monitoring of the difference between the body-building action and the standard action of the body-building person in the body-building process, effectively improves the body-building efficiency and also improves the use experience of the body-building person.
For example, referring to fig. 3, fig. 3 illustrates a difficulty often existing in the prior art, when a user 102 is in front of a mirror 101, a reflected image 103 of a user's body is reflected by the mirror 101, and when the first image data 104 is acquired and directly displayed, there is a significant scale difference or a location difference between the reflected image 103 and the first image data 104.
For example, referring to fig. 4, fig. 4 shows a specific effect of the present embodiment, similarly, when the user 102 is in front of the mirror 101, the mirror 101 reflects the reflected image 103 of the user's body, and when the first image data is acquired and corrected, the corrected first image data 105 and the reflected image 103 are roughly overlapped in a certain preset posture, so that when the user 102 makes a motion corresponding to the corrected first image data 105 in front of the mirror 101, a difference between the corrected first image data 105 and the reflected image 103 of the mirror 101 can be visually seen.
In a more specific embodiment, step S2 includes the following sub-steps:
s21: extracting coordinate data of the characteristic points from the first image data to form first coordinate data, and extracting coordinate data of the corresponding characteristic points from the second image data to form second coordinate data;
s22: and correcting each frame in the first image data according to the difference between the second coordinate data and the first coordinate data until a preset condition is met.
In this embodiment, as a more specific implementation manner, the first image data correction is performed by extracting the feature points, and it should be understood that, in step S1, the feature points extracted from the first image data and the feature points extracted from the second image data should correspond to each other, and the correspondence relationship may be approximately the same points located at approximately the same positions. Similarly, the modification of the first image data should be performed for each frame, and the specific modification process may perform the modification for each frame at the same time, or perform continuous modification for the following frames while playing the modified first image data, and whatever modification method is used for the modification, should be considered to be within the scope of the present embodiment.
In a more specific embodiment, extracting the coordinate data of the feature point from the first image data to form first coordinate data, and extracting the coordinate data of the corresponding feature point from the second image data to form second coordinate data includes:
selecting a frame of which the coach reaches a preset posture from first image data as a first key frame, and extracting the outline of a coach preset part in the first key frame;
selecting a frame of which the user achieves the same preset posture from second image data as a second key frame, and extracting the outline of the same preset part of the user in the second key frame;
and extracting feature points based on the first keyframe corresponding contour and generating first coordinate data, and extracting feature points based on the second keyframe corresponding contour and generating second coordinate data.
In this embodiment, in order to extract the same or similar feature points, the postures and the parts of the feature points extracted from the first image data and the second image data need to be kept consistent, the preset postures in this embodiment may adopt postures convenient for a user to keep, such as a fixed standing posture, a fixed sitting posture, a fixed lying posture, and the like, and for the preset parts, parts easy to recognize, such as upper arms, thighs, shoulders, and the like, or multiple parts may be used as the preset parts at the same time. Illustratively, the upper arm and the thigh are simultaneously used as the preset part, and the first image data is corrected by the position relation of the characteristic points on the upper arm and the thigh. It should be understood that any extraction method in the prior art may be used to extract the feature points from the contour, and since the contour lines are often generated through the feature points, the feature points that generate the contour lines are used as the feature points in this embodiment, or points that are more suitable for the requirement are extracted on the contour line after the contour lines are generated as the feature points, which is not limited in this embodiment.
In a more specific embodiment, extracting feature points based on the contour includes:
extracting at least three points in the contour as the feature points, wherein the feature points are inflection points in the contour;
the feature points extracted based on the first keyframe correspond to the feature points extracted based on the second keyframe.
In this embodiment, the positions and positions of the feature points extracted from the first key frame should be substantially the same as those of the second key frame, the specific positions and positions of the feature points can be selected by a preset method, and the accuracy of the detection result can be ensured by extracting at least three feature points; the most prominent feature in the same general contour line will be characterized as an inflection point on the contour line, so the inflection point in the contour is adopted as the feature point in the present embodiment.
In one embodiment, modifying each frame in the first image data to satisfy a preset condition according to the difference between the second coordinate data and the first coordinate data comprises:
forming user body size data based on the second coordinate data and forming coach body size data based on the first coordinate data;
cropping and/or scaling each frame in the first image data in at least one direction according to a ratio of the user physique size data to the coach physique size data in that direction.
In this embodiment, in order to realize quick modification of the first image data, the size data is formed by the coordinate data in this embodiment, and the forming manner may be, for example, an euler distance between feature points. Illustratively, two feature points corresponding to the second coordinate data are connected, two feature points corresponding to the first coordinate data are connected, and the first image data is stretched or compressed along the connection direction according to the ratio of the lengths of the connection lines.
For example, after the first image data is stretched or compressed along the link direction according to the ratio of the lengths of the links, a link between the feature points may be selected in a direction orthogonal to the current stretching or compressing direction, and the first image data is stretched or compressed along the link direction according to the ratio of the lengths of the links.
Based on the same inventive concept, please refer to fig. 2 in combination, a functional block diagram of a mirror-surface exercise information interaction system is also provided, and the detailed description of the mirror-surface exercise information interaction system is as follows.
A mirror-type fitness information interaction system, comprising:
a processor configured to obtain a fitness video stream as first image data;
a mirror configured to reflect an image of a user;
a camera configured to acquire an image reflected by a user at the mirror surface as second image data;
a display disposed below the mirror surface;
the processor corrects the first image data according to the second image data until a preset condition is met; the preset condition is that the physical size of the coach in the corrected first image data corresponds to the physical size of the user in the second image data;
the display displays the corrected first image data and is overlapped on the reflection image on the mirror surface; and when the action of the coach in the corrected first image data is the same as the action of the user in the reflected image, the shape of the coach in the image displayed by the display is superposed with the shape of the user in the reflected image.
In one embodiment, the processor is further configured to modify the first image data according to the second image data to satisfy a preset condition, including:
the processor extracts coordinate data of the characteristic points from the first image data to form first coordinate data, and extracts coordinate data of the corresponding characteristic points from the second image data to form second coordinate data;
and the processor corrects each frame in the first image data according to the difference between the second coordinate data and the first coordinate data until a preset condition is met.
In one embodiment, the processor is further configured to select a frame of the first image data in which the coach achieves a preset posture as a first key frame, and extract a contour of a coach preset part in the first key frame;
the processor selects frames of which the users reach the same preset posture from the second image data as second key frames, and extracts the outlines of the same preset parts of the users in the second key frames;
the processor extracts feature points based on the first keyframe corresponding contours and generates first coordinate data, and extracts feature points based on the second keyframe corresponding contours and generates second coordinate data.
In one embodiment, the processor is further configured to extract at least three points in the contour as the feature points, the feature points being inflection points in the contour;
the feature points extracted by the processor based on the first keyframe correspond to feature points extracted based on the second keyframe.
In one embodiment, the processor is further configured to form user physique size data based on the second coordinate data and coach physique size data based on the first coordinate data;
the processor cropping and/or scaling each frame in the first image data in at least one direction according to a ratio of the user physical size data to the coach physical size data in that direction.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electric, mechanical or other form of connection.
The elements described as separate parts may or may not be physically separate, as one of ordinary skill in the art would appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general sense in the foregoing description for clarity of explanation of the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a grid device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A mirror-type fitness information interaction method is characterized by comprising the following steps:
acquiring a fitness video stream as first image data, and acquiring an image reflected by a mirror surface of a user as second image data;
correcting the first image data according to the second image data until a preset condition is met; the preset condition is that the physical size of the coach in the corrected first image data corresponds to the physical size of the user in the second image data;
displaying the corrected first image data at the mirror surface and overlapping the reflected image on the mirror surface; the action of the coach in the modified first image data is the same as the action of the user in the reflected image, and the shape of the coach in the modified first image data is superposed with the shape of the user in the reflected image.
2. The mirror-type exercise information interaction method of claim 1, wherein the modifying the first image data according to the second image data to satisfy a preset condition comprises:
extracting coordinate data of the characteristic points from the first image data to form first coordinate data, and extracting coordinate data of the corresponding characteristic points from the second image data to form second coordinate data;
and correcting each frame in the first image data according to the difference between the second coordinate data and the first coordinate data until a preset condition is met.
3. The mirror-type fitness information interaction method of claim 2, wherein extracting coordinate data of feature points from the first image data to form first coordinate data, and extracting coordinate data of corresponding feature points from the second image data to form second coordinate data comprises:
selecting a frame of which the coach reaches a preset posture from first image data as a first key frame, and extracting the outline of a coach preset part in the first key frame;
selecting a frame of which the user achieves the same preset posture from second image data as a second key frame, and extracting the outline of the same preset part of the user in the second key frame;
and extracting feature points based on the first keyframe corresponding contour and generating first coordinate data, and extracting feature points based on the second keyframe corresponding contour and generating second coordinate data.
4. The mirror-type fitness information interaction method of claim 3, wherein extracting feature points based on contours comprises:
extracting at least three points in the contour as the feature points, wherein the feature points are inflection points in the contour;
the feature points extracted based on the first keyframe correspond to the feature points extracted based on the second keyframe.
5. The method of claim 3, wherein modifying each frame of the first image data according to the difference between the second coordinate data and the first coordinate data to satisfy a predetermined condition comprises:
forming user body size data based on the second coordinate data and forming coach body size data based on the first coordinate data;
cropping and/or scaling each frame in the first image data in at least one direction according to a ratio of the user physique size data to the coach physique size data in that direction.
6. A mirror-based fitness information interaction system, comprising:
a processor configured to obtain a fitness video stream as first image data;
a mirror configured to reflect an image of a user;
a camera configured to acquire an image reflected by a user at the mirror surface as second image data;
a display disposed below the mirror surface;
the processor corrects the first image data according to the second image data until a preset condition is met; the preset condition is that the physical size of the coach in the corrected first image data corresponds to the physical size of the user in the second image data;
the display displays the corrected first image data and is overlapped on the reflection image on the mirror surface; and when the action of the coach in the corrected first image data is the same as the action of the user in the reflected image, the shape of the coach in the image displayed by the display is superposed with the shape of the user in the reflected image.
7. The mirror-like fitness information interaction system of claim 6, wherein the processor is further configured to modify the first image data according to the second image data to satisfy a preset condition comprises:
the processor extracts coordinate data of the characteristic points from the first image data to form first coordinate data, and extracts coordinate data of the corresponding characteristic points from the second image data to form second coordinate data;
and the processor corrects each frame in the first image data according to the difference between the second coordinate data and the first coordinate data until a preset condition is met.
8. The mirror-like fitness information interaction system of claim 7, wherein the processor is further configured to select a frame of the trainer reaching a preset posture from the first image data as a first key frame, and extract a contour of a preset portion of the trainer in the first key frame;
the processor selects frames of which the users reach the same preset posture from the second image data as second key frames, and extracts the outlines of the same preset parts of the users in the second key frames;
the processor extracts feature points based on the first keyframe corresponding contours and generates first coordinate data, and extracts feature points based on the second keyframe corresponding contours and generates second coordinate data.
9. The interactive mirror-like fitness information system of claim 8, wherein the processor is further configured to extract at least three points in the contour as the feature points, wherein the feature points are inflection points in the contour;
the feature points extracted by the processor based on the first keyframe correspond to feature points extracted based on the second keyframe.
10. The mirror-like fitness information interaction system of claim 8, wherein the processor is further configured to form user physique size data based on the second coordinate data and coach physique size data based on the first coordinate data;
the processor cropping and/or scaling each frame in the first image data in at least one direction according to a ratio of the user physical size data to the coach physical size data in that direction.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111216065.6A CN113935921A (en) | 2021-10-19 | 2021-10-19 | Mirror-surface type fitness information interaction method and system |
| PCT/CN2022/121809 WO2023065991A1 (en) | 2021-10-19 | 2022-09-27 | Mirror type fitness information interaction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111216065.6A CN113935921A (en) | 2021-10-19 | 2021-10-19 | Mirror-surface type fitness information interaction method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113935921A true CN113935921A (en) | 2022-01-14 |
Family
ID=79280513
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111216065.6A Pending CN113935921A (en) | 2021-10-19 | 2021-10-19 | Mirror-surface type fitness information interaction method and system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113935921A (en) |
| WO (1) | WO2023065991A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023065991A1 (en) * | 2021-10-19 | 2023-04-27 | 成都拟合未来科技有限公司 | Mirror type fitness information interaction method and system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012039467A1 (en) * | 2010-09-22 | 2012-03-29 | パナソニック株式会社 | Exercise assistance system |
| CN108525261A (en) * | 2018-05-22 | 2018-09-14 | 深圳市赛亿科技开发有限公司 | A kind of Intelligent mirror exercise guide method and system |
| KR102457296B1 (en) * | 2018-05-29 | 2022-10-21 | 큐리어서 프로덕츠 인크. | Reflective video display device and methods of use for interactive training and demonstration |
| CN113935921A (en) * | 2021-10-19 | 2022-01-14 | 成都拟合未来科技有限公司 | Mirror-surface type fitness information interaction method and system |
-
2021
- 2021-10-19 CN CN202111216065.6A patent/CN113935921A/en active Pending
-
2022
- 2022-09-27 WO PCT/CN2022/121809 patent/WO2023065991A1/en unknown
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023065991A1 (en) * | 2021-10-19 | 2023-04-27 | 成都拟合未来科技有限公司 | Mirror type fitness information interaction method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023065991A1 (en) | 2023-04-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230338778A1 (en) | Method and system for monitoring and feed-backing on execution of physical exercise routines | |
| US4891748A (en) | System and method for teaching physical skills | |
| Chen et al. | Computer-assisted self-training system for sports exercise using kinects | |
| JP6124308B2 (en) | Operation evaluation apparatus and program thereof | |
| US20100220897A1 (en) | Information processing apparatus and network conference system | |
| CN110838353A (en) | Action matching method and related product | |
| CN107930048B (en) | Space somatosensory recognition motion analysis system and motion analysis method | |
| WO2019116495A1 (en) | Technique recognition program, technique recognition method, and technique recognition system | |
| CN110780742B (en) | Eyeball tracking processing method and related device | |
| JP2015186531A (en) | Action information processing device and program | |
| CN113409651B (en) | Live broadcast body building method, system, electronic equipment and storage medium | |
| CN113935921A (en) | Mirror-surface type fitness information interaction method and system | |
| CN111967407A (en) | Action evaluation method, electronic device, and computer-readable storage medium | |
| Tharatipyakul et al. | Pose estimation for facilitating movement learning from online videos | |
| JP2001236505A (en) | Method, device and system for estimating coordinate | |
| CN110070036A (en) | The method, apparatus and electronic equipment of synkinesia action training | |
| CN113342157B (en) | Eyeball tracking processing method and related device | |
| EP4097709A1 (en) | Exercise instruction and feedback systems and methods | |
| CN113345552A (en) | Method and system for intelligently assisting in guiding dance exercises and mobile terminal | |
| WO2023193333A1 (en) | Fitness shaping course display device and method | |
| Li et al. | Fitness coach: Design and implementation of a smart mirror based on automatic image recognition and action model comparison | |
| WO2023193338A1 (en) | Pacing device and method | |
| CN116071814A (en) | Gesture monitoring method and device, electronic equipment, computer readable medium and product | |
| US20230126755A1 (en) | Information processing apparatus, information processing method, and imaging system | |
| WO2022230373A1 (en) | Posture evaluation system, posture evaluation program, posture evaluation method, and posture evaluation device |
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 |