CN111666844A - Badminton player motion posture assessment method - Google Patents
Badminton player motion posture assessment method Download PDFInfo
- Publication number
- CN111666844A CN111666844A CN202010453320.8A CN202010453320A CN111666844A CN 111666844 A CN111666844 A CN 111666844A CN 202010453320 A CN202010453320 A CN 202010453320A CN 111666844 A CN111666844 A CN 111666844A
- Authority
- CN
- China
- Prior art keywords
- point
- posture
- skeleton
- model
- attitude
- 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
Images
Classifications
-
- 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
- G06V40/23—Recognition of whole body movements, e.g. for sport training
-
- 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
Abstract
The invention relates to the field of human body posture assessment, in particular to a badminton player motion posture assessment method; the method comprises the following steps: s1: inputting skeleton point coordinates of a posture model to be detected; s2: carrying out coordinate conversion and calculating a vector included angle; s3: calculating the accumulated difference value of the attitude model to be measured; s4: and calculating the accumulated error and outputting the serial number of the attitude model with the minimum accumulated error. The method searches the data of the candidate attitude library by means of a group of skeleton point coordinates of badminton under an image pixel coordinate system, matches an optimal attitude model and calculates an accumulated error in the searching process, evaluates the motion attitude model through a matching stage and the accumulated error, provides a new quantitative standard, and compared with the traditional action recognition method based on machine learning, quantifies the similarity between the human body attitude and the standard attitude by using the accumulated error, and can more accurately compare the difference of the human body attitude from the data level.
Description
Technical Field
The invention relates to the field of evaluation of human body posture models, in particular to a badminton player motion posture evaluation method.
Background
In the process of badminton player sports, high requirements are placed on the standard degree of self action, but the training always depends on the correction of the posture of the badminton player by a coach, and no accurate evaluation system is provided.
However, in the field of human body posture model evaluation, most of the methods convert the human body posture model coordinates in the image pixel coordinate system into the world coordinate system, and then evaluate the human body posture model in the three-dimensional space.
Disclosure of Invention
The invention aims to: aiming at the problems that the calculation is complex and impractical and the difference between the motion attitude and the standard attitude cannot be accurately found in two dimensions in the motion attitude assessment method for badminton players in the prior art, the motion attitude assessment method for the badminton players is provided. In order to achieve the purpose, the invention adopts the technical scheme that:
a badminton player sports posture assessment method comprises the following steps:
s1: inputting a group of human skeleton point coordinates of the posture model to be detected under an image pixel coordinate system, and judging the legality of the human skeleton point coordinates;
s2: performing coordinate conversion on each human body skeleton point coordinate judged by legality, converting an image pixel coordinate system into a rectangular coordinate system with 0 point as an origin, and respectively calculating a vector from each human body skeleton point coordinate to 0 point and a skeleton point included angle formed by the vector and the positive direction of the x axis of the rectangular coordinate system;
s3: setting the priority of each skeleton point, sequentially taking one skeleton point and corresponding skeleton points of all posture models in the candidate posture set according to the priority to calculate an accumulated difference value, outputting the accumulated difference value, and entering step S4 after all skeleton points of the posture model to be detected are calculated;
wherein, the accumulated difference is the absolute value of the difference of the included angles of the skeleton points in the step S2, and the candidate posture set is initially a preset human posture standard library;
s4: calculating accumulated errors, searching a posture model with the minimum accumulated error in the candidate posture set, outputting a posture model serial number and the accumulated errors; and the accumulated error is the sum of accumulated differences of all skeleton points of the posture model to be detected in the posture model in a candidate posture set. The method searches data of a standard action library by means of a group of skeleton point coordinates of badminton under an image pixel coordinate system, matches an optimal posture model and calculates an accumulated error in the searching process, and evaluates the motion posture model through a matching stage and the accumulated error. And the concept of accumulated errors is applied to the evaluation of the human body postures of the badminton players, a new quantification standard is provided, and compared with the traditional action recognition method based on machine learning, the similarity between the human body postures and the standard postures is quantified by the accumulated errors, and the difference of the human body postures can be compared more accurately from a data layer.
As a preferred scheme of the invention, the human skeleton point coordinates of the posture model to be detected include 13 point coordinates which are respectively a rock point (neck point), an Rshoulder point (right shoulder point), a relabow point (right elbow point), an Rwrist point (right wrist point), an Lshoulder point (left shoulder point), a Leblow point (left elbow point), an Lwrist point (left wrist point), a Rhip point (right hip point), an rkne point (right knee point), a Rankle point (right ankle point), an Lhip point (left hip point), an lkne point (left knee point) and a Rankle point (left ankle point), and are sequentially numbered from 0 to 12, wherein the rock point is 0 point. The invention applies the idea of local evaluation to the evaluation of the human body posture of the badminton player and provides a new human body posture model. The strategy uses a 13-point human body posture model designed aiming at the motion posture of a badminton player, divides the upper and lower limb areas into an upper limb right area, an upper limb left area, a lower limb right area and a lower limb left area according to the angle of image acquisition, and cancels the evaluation of the head area. The traditional human body posture assessment is universal human body posture assessment, and the assessment posture range comprises walking, running, waving hands and even comparison with various sports, so that the traditional human body posture model covers the whole body on the distribution of human body posture skeleton points, the badminton belongs to upper limb sports, the contribution degree of limbs to the posture is enlarged by using the new human body posture model, and the influence of irrelevant skeleton points on the posture is eliminated.
As a preferable aspect of the present invention, the validity judgment in step S1 includes the steps of:
s11: judging whether the coordinates of the human skeleton points in the input posture model to be detected accord with the coordinates of the human skeleton points at 13 points, if not, inputting the coordinates again;
s12: and judging whether the 0 point in the coordinates of the human skeleton point in the input posture model to be detected is (0, 0), and if so, re-inputting the coordinates.
As a preferable embodiment of the present invention, the step S3 includes the steps of:
s31: setting the priority of each skeleton point;
s32: sequentially selecting a skeleton point of the posture model to be detected according to the priority;
s33: calculating the accumulated difference value of the bone point included angle of the bone point and the bone point included angle of the corresponding bone point of each posture model in the candidate posture set;
s34: comparing the accumulated difference values of all the attitude models with corresponding preset errors in sequence;
when the accumulated difference is smaller than or equal to the preset error, recording a corresponding attitude model serial number; when the accumulated difference is larger than the preset error, deleting the attitude model corresponding to the attitude model serial number from the candidate attitude set; after comparing all the pose models in the candidate pose set, the method proceeds to step S35;
s35: judging whether all the included angles of the skeleton points of the posture model to be detected are calculated or not, and if not, entering the step S33; if the step is completed, the process proceeds to step S4.
As a preferable embodiment of the present invention, the step S34 is followed by the following steps:
and judging whether the candidate posture set is empty, if so, outputting the name of the bone point calculated at the moment and the posture model serial number in the candidate posture set during the calculation of the last bone point, and entering the step S4, otherwise, continuing to perform the step S35.
As a preferred embodiment of the present invention, the bone points are ranked from high to low in priority as a rock point, an Rshoulder point, a relalow point, an Lwrist point, an Rhip point, an Rknee point, a Rankle point, an Lhip point, an Lknee point, a Rankle point, an Rwrist point, an Lshoulder point, and a lebow point, and the corresponding rank is ranked as 1, 2, 3, 7, 8, 9, 10, 11, 12, 4, 5, and 6, and the bone points with high priority are preferentially involved in the calculation. The invention applies the concept of priority to the evaluation of the human body posture of the badminton player and provides a new evaluation strategy. According to the new human body posture model, the priority of skeleton points in each area is subdivided, so that the interference of the camera view angle can be eliminated, and the motion posture of a badminton player can be better judged.
As a preferred embodiment of the present invention, the Rwrist point, the Lshoulder point, and the lebow point with lower priority are omitted in the calculation. According to the invention, 3 bone points with the lowest priority are excluded from calculation, so that the calculation process of the method is optimized as much as possible, and the calculation amount is reduced.
As a preferable aspect of the present invention, the preset error corresponding to the rock point, the Rshoulder point, the relabow point, the Lwrist point, the Rhip point, the Rknee point, the Rankle point, the Lhip point, the Lknee point, and the Rankle point is {5,10,10,5,10,10, 10 }.
As a preferred embodiment of the present invention, the set of candidate poses is initially a pre-defined standard library of body poses, the standard library of body poses comprising at least 7 frames of images.
An electronic device comprising at least one processor, and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor to enable the at least one processor to perform any of the methods described above.
In summary, due to the adoption of the technical scheme, the invention has the beneficial effects that:
1. the invention applies the concept of accumulated error to the evaluation of the human body posture of the badminton player and provides a new quantitative standard. Compared with the traditional action recognition method based on machine learning, the method quantifies the similarity between the human body posture and the standard posture by using the accumulated error, and can more accurately compare the difference of the human body posture from a data layer.
2. The invention applies the idea of local evaluation to the evaluation of the human body posture of the badminton player and provides a new human body posture model. The strategy uses a 13-point human body posture model designed aiming at the motion posture of a badminton player, divides the upper and lower limb areas into an upper limb right area, an upper limb left area, a lower limb right area and a lower limb left area according to the angle of image acquisition, and cancels the evaluation of the head area. The traditional human body posture assessment is universal human body posture assessment, and the assessment posture range comprises walking, running, waving hands and even comparison with various sports, so that the traditional human body posture model covers the whole body on the distribution of human body posture skeleton points, the badminton belongs to upper limb sports, the contribution degree of limbs to the posture is enlarged by using the new human body posture model, and the influence of irrelevant skeleton points on the posture is eliminated.
3. The invention applies the concept of priority to the evaluation of the human body posture of the badminton player and provides a new evaluation strategy. According to the new human body posture model, the priority of skeleton points in each area is subdivided, so that the interference of the camera view angle can be eliminated, and the motion posture of a badminton player can be better judged.
Drawings
Fig. 1 is a flowchart of a badminton player sports posture assessment method according to embodiment 1 of the present invention.
Fig. 2 is a 13-point human posture model of a badminton player sports posture assessment method in embodiment 1 of the invention.
Fig. 3 is an image pixel coordinate system of the badminton player sports attitude assessment method in embodiment 1 of the present invention.
Fig. 4 is a rectangular coordinate system with 0 point (tack) as the origin according to the badminton player sports gesture evaluation method in embodiment 1 of the present invention.
Fig. 5 is an image of a badminton player during the establishment of a human posture standard library according to the badminton posture assessment method in embodiment 1 of the present invention.
Fig. 6 is a subarea of a human posture model of the badminton player sports posture evaluation method in embodiment 1 of the invention.
Fig. 7 shows 138 to 145 video images of a badminton player in the method for evaluating a sports pose according to embodiment 1 of the present invention.
Fig. 8 is an evaluation result of 138-145 frames of images of a certain video according to the badminton player sports posture evaluation method in embodiment 1 of the present invention.
Fig. 9 is an electronic device according to embodiment 2 of the present invention, which utilizes the badminton player sports posture assessment method according to embodiment 1.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings.
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Example 1
As shown in fig. 1, a badminton player sports posture assessment method includes the following steps:
s1: inputting a group of human skeleton point coordinates of the posture model to be detected under an image pixel coordinate system, and judging the legality of the coordinates; as shown in fig. 2, the human skeleton point coordinates of the posture model to be measured include 13 point coordinates, which are a rock point (neck point), an Rshoulder point (right shoulder point), a relabow point (right elbow point), an Rwrist point (right wrist point), an Lshoulder point (left shoulder point), an Leblow point (left elbow point), an Lwrist point (left wrist point), an Rhip point (right hip point), an rkne point (right knee point), a Rankle point (right ankle point), an Lhip point (left hip point), an Lknee point (left knee point) and a Rankle point (left ankle point), and are sequentially numbered as 0-12, wherein the rock point is 0 point.
S2: the coordinates of the human skeleton points judged by the legality are subjected to coordinate conversion, an image pixel coordinate system is converted into a rectangular coordinate system with 0 point as an original point, each vector from the human skeleton point coordinates to the 0 point and a skeleton point included angle formed by the vector and the rectangular coordinate system in the positive direction of the x axis are calculated respectively, the image pixel coordinate system is shown in fig. 3, and the rectangular coordinate system is shown in fig. 4.
S3: setting the priority of each skeleton point, sequentially taking one skeleton point and corresponding skeleton points of all postures in the candidate posture set according to the priority to calculate an accumulated difference value, outputting the accumulated difference value, and entering step S4 after all the skeleton points of the posture to be detected are calculated;
wherein the accumulated difference is the absolute value of the difference between the included angles in step S2, the candidate pose set is initially a preset body pose standard library, as shown in fig. 5, the body pose standard library includes at least 7 frames of images, {0, 1, 2} is forward-handed ball picking, {4, 5, 6} is backward-handed ball picking, {7} is ball jumping; under the condition of ensuring the integrity of the input human body posture coordinate set, the manufacturing process is steps S1 to S3, and the corresponding bone point included angle set is obtained to be the characteristic of the standard posture.
S4: calculating the accumulated error in the process, searching the attitude model with the minimum accumulated error in the candidate attitude set, and outputting the serial number of the attitude model and the accumulated error; the accumulated error is the sum of accumulated differences of all skeleton points of the posture model to be tested in the posture model of a candidate posture set, the accumulated error represents the similarity degree of the posture to be evaluated and the standard posture, and the smaller the accumulated error is, the higher the similarity degree is.
Specifically, the validity judgment in step S1 includes the following steps:
s11: and judging whether the coordinates of the human skeleton points in the input posture model to be detected accord with the coordinates of the human skeleton points at 13 points, if not, inputting the coordinates again.
S12: and judging whether the 0 point in the coordinates of the human skeleton point in the input posture model to be detected is (0, 0), and if so, re-inputting the coordinates.
The step S2 includes:
s21: input human skeleton point coordinates { a }0,a1,...,a12In the image pixel coordinate system, with a0A rectangular coordinate system is constructed for the origin, with the x-axis from left to right in the horizontal direction and the y-axis from top to bottom in the vertical direction.
S22: coordinates of other human skeleton points { a }1,...,a12Subtract a0Then, a vector set { t is calculated0,t1,...,t11I is the mark of human skeleton point, tiIs a vector between the bone points i and 0.
S23: using formulas
Calculating the included angle formed by each vector in the vector set and the positive direction of the x axis in a counterclockwise manner to obtain an included angle set { theta0,θ1,...,θ11Therein of
tiyIs a vector tiThe value on the y-axis.
Steps S21 and S22 are performed because the player' S position in the badminton court is different, which causes a problem in matching with the standard posture, and even a certain posture, if it occurs in a different position in the badminton court, it exhibits different coordinates in the camera view. The positions of the remaining 12 bone points are determined with respect to the neck, which is the origin regardless of the standard posture or the input player posture, through S21 and S22, which can eliminate the problem due to the difference in position.
Step S23 is performed because the pose estimation must exclude the influence of individual differences, and therefore the included angle in the rectangular coordinate system solution S23 is used to eliminate the uncertainty caused by such individual differences.
The step S3 includes the steps of:
s31: setting the priority of each skeleton point;
s32: sequentially selecting skeleton points of the posture model to be detected according to the priority, and calculating the accumulated difference of the included angle of the skeleton points and the included angle of the corresponding skeleton point of each posture model in the candidate posture set;
s33: sequentially selecting a skeleton point of the posture model to be detected according to the priority;
s34: as shown in the figure, the accumulated difference values of all the attitude models are compared with corresponding preset errors in sequence;
when the accumulated difference is smaller than or equal to the preset error, recording a corresponding attitude model serial number; when the accumulated difference is larger than the preset error, deleting the attitude model corresponding to the attitude model serial number from the candidate attitude set; after comparing all the posture models in the candidate posture set, judging whether the candidate posture set is empty, if the candidate posture set is empty, outputting the name of the bone point calculated at the moment and the serial number of the posture model in the candidate posture set during the calculation of the last bone point, and entering step S4, if the candidate posture set is not empty, entering step S35;
s35: judging whether all the included angles of the skeleton points of the posture model to be detected are calculated or not, and if not, entering the step S33; if the step is completed, the process proceeds to step S4.
The calculation process of the accumulated difference value of one bone point of the posture model to be detected is as follows:
1) selecting a posture model in the candidate posture set according to the sequence of the posture models;
2) calculating the included angle theta of the skeleton points of the posture model to be measurediBone point included angle theta corresponding to the candidate attitude centralized attitude modeli *The absolute value of the difference is recorded as an accumulated difference;
3) judging whether all the attitude models in the candidate attitude set are calculated; if not, entering the step 1) to select the next attitude model in the candidate attitude set for calculation; and if the calculation is finished, the calculation of the accumulated difference value of the skeleton point of the posture model to be measured is finished.
After the coordinate transformation of S2, there are 12 skeleton points in total, and as shown in fig. 6, the vector set formed by the 12 skeleton points is divided into four regions, which are the upper limb right region { θ }0,θ1,θ2The left region of the upper limb { theta }3,θ4,θ5}, lower limb right region { theta6,θ7,θ8And left region of lower limb { theta }9,θ10,θ11}. The priority order of each bone point is { theta }0,θ1,θ2,θ6,θ7,θ8,θ9,θ10,θ11And the Rwrist point, the Lshoulder point and the Leblob point with lower priority are ignored, the calculation process of the invention is optimized as much as possible, and the calculation amount is reduced. Wherein the preset error corresponding to the sock point, the Rshoulder point, the relabow point, the Lwrist point, the Rhip point, the Rknee point, the Rankle point, the Lhip point, the Lknee point, and the Rankle point is {5,10,10,5,10,10 }. It can be understood that, when the badminton player carries out right-hand shooting in the sports process, the upper limb right area is a key area for evaluating the sports posture and needs to be distinguished from other areas, and the lower limb area and the upper limb left area are mainly used for balancing the body and do not contribute much to the sports posture. Meanwhile, a large number of phenomena that the right area of the limb blocks the left area appear in the image acquired from the right side, and the reliability of the coordinate of the skeletal point of the right area of the limb is higher than that of the left area no matter what type of the acquired posture coordinate of the human body.
As shown in fig. 7 and 8, the matching images from 138 frames to 145 frames of a certain video and the matching results from 138 frames to 145 frames of the certain video are obtained by the method of the present invention.
Example 2
As shown in fig. 9, an electronic device includes at least one processor, and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method of assessing the sports pose of a shuttlecock player as described in the previous embodiments. The input and output interface can comprise a display, a keyboard, a mouse and a USB interface and is used for inputting and outputting data; the power supply is used for supplying electric energy to the electronic equipment.
Those skilled 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 includes: various media that can store program codes, such as a removable Memory device, a Read Only Memory (ROM), a magnetic disk, or an optical disk.
When the integrated unit of the present invention is implemented in the form of a software functional unit and sold or used as a separate product, it may also be stored in a computer-readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a magnetic or optical disk, or other various media that can store program code.
It should be noted that, for the embodiments of the apparatus and the electronic device, since they are basically similar to the embodiments of the method, the description is relatively simple, and the relevant points can be referred to the partial description of the embodiments of the method.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. A badminton player sports posture assessment method is characterized in that: the method comprises the following steps:
s1: inputting a group of human skeleton point coordinates of the posture model to be detected under an image pixel coordinate system, and judging the legality of the human skeleton point coordinates;
s2: performing coordinate conversion on each human body skeleton point coordinate judged by legality, converting an image pixel coordinate system into a rectangular coordinate system with 0 point as an origin, and respectively calculating a vector from each human body skeleton point coordinate to 0 point and a skeleton point included angle formed by the vector and the positive direction of the x axis of the rectangular coordinate system;
s3: setting the priority of each skeleton point, sequentially taking one skeleton point and corresponding skeleton points of all posture models in the candidate posture set according to the priority to calculate an accumulated difference value, outputting the accumulated difference value, and entering step S4 after all skeleton points of the posture model to be detected are calculated;
wherein, the accumulated difference is the absolute value of the difference of the included angles of the skeleton points in the step S2, and the candidate posture set is initially a preset human posture standard library;
s4: calculating accumulated errors, searching a posture model with the minimum accumulated error in the candidate posture set, outputting a posture model serial number and the accumulated errors; and the accumulated error is the sum of accumulated differences of all skeleton points of the posture model to be detected in the posture model in a candidate posture set.
2. The method of claim 1, wherein the method comprises the steps of: the human skeleton point coordinates of the posture model to be detected comprise 13 point coordinates which are respectively a rock point, an Rshoulder point, a Relbow point, an Rwrist point, an Lshoulder point, a Leblock point, an Lwrist point, an Rhip point, an Rknee point, a Rankle point, an Lhip point, an Lknee point and a Rankle point, and are sequentially marked as 0-12, wherein the rock point is 0 point.
3. The method of claim 2, wherein the method comprises the steps of: the validity judgment in the step S1 includes the following steps:
s11: judging whether the coordinates of the human skeleton points in the input posture model to be detected accord with the coordinates of the human skeleton points at 13 points, if not, inputting the coordinates again;
s12: and judging whether the 0 point in the coordinates of the human skeleton point in the input posture model to be detected is (0, 0), and if so, re-inputting the coordinates.
4. The method of claim 2, wherein the method comprises the steps of: the step S3 includes the steps of:
s31: setting the priority of each skeleton point;
s32: sequentially selecting a skeleton point of the posture model to be detected according to the priority;
s33: calculating the accumulated difference value of the bone point included angle of the bone point and the bone point included angle of the corresponding bone point of each posture model in the candidate posture set;
s34: comparing the accumulated difference values of the attitude models with corresponding preset errors in sequence;
when the accumulated difference is smaller than or equal to the preset error, recording a corresponding attitude model serial number; when the accumulated difference is larger than the preset error, deleting the attitude model corresponding to the attitude model serial number from the candidate attitude set; after comparing all the pose models in the candidate pose set, the method proceeds to step S35;
s35: judging whether all the included angles of the skeleton points of the posture model to be detected are calculated or not, and if not, entering the step S33; if the step is completed, the process proceeds to step S4.
5. The method of claim 4 for assessing the sports pose of a badminton player, the method comprising: the step S34 is followed by the following steps:
and judging whether the candidate posture set is empty, if so, outputting the name of the bone point calculated at the moment and the posture model serial number in the candidate posture set during the calculation of the last bone point, and entering the step S4, otherwise, continuing to perform the step S35.
6. The method of claim 5, wherein the method comprises the steps of: the bone points are ranked from high to low in priority as a rock point, a Rshoulder point, a Relbow point, a Lwrist point, a Rhip point, a Rknee point, a Rankle point, a Lhip point, a Lknee point, a Rankle point, a Rwrist point, a Lshoulder point and a Leblob point, corresponding sequence numbers are ranked as 1, 2, 3, 7, 8, 9, 10, 11, 12, 4, 5 and 6, and the bone points with high priority are preferentially involved in calculation.
7. The method of claim 6, wherein the method comprises the steps of: the Rwrist point, the Lshoulder point, and the lebow point, which are lower in priority, are ignored in the calculation.
8. The method of claim 7, wherein the method comprises the steps of: the preset error corresponding to the sock point, the Rshoulder point, the relabow point, the Lwrist point, the Rhip point, the Rknee point, the Rankle point, the Lhip point, the Lknee point, and the Rankle point is {5,10,10,5,10,10,5 }.
9. The method of claim 1, wherein the method comprises the steps of: the body pose standard library includes at least 7 frames of images.
10. An electronic device comprising at least one processor, and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010453320.8A CN111666844A (en) | 2020-05-26 | 2020-05-26 | Badminton player motion posture assessment method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010453320.8A CN111666844A (en) | 2020-05-26 | 2020-05-26 | Badminton player motion posture assessment method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111666844A true CN111666844A (en) | 2020-09-15 |
Family
ID=72384492
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010453320.8A Pending CN111666844A (en) | 2020-05-26 | 2020-05-26 | Badminton player motion posture assessment method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111666844A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112818800A (en) * | 2021-01-26 | 2021-05-18 | 中国人民解放军火箭军工程大学 | Physical exercise evaluation method and system based on human skeleton point depth image |
| CN116052273A (en) * | 2023-01-06 | 2023-05-02 | 北京体提科技有限公司 | Action comparison method and device based on body state fishbone line |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109685013A (en) * | 2018-12-25 | 2019-04-26 | 上海智臻智能网络科技股份有限公司 | The detection method and device of header key point in human body attitude identification |
| CN109753891A (en) * | 2018-12-19 | 2019-05-14 | 山东师范大学 | Football player's orientation calibration method and system based on human body critical point detection |
| 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 |
| CN110007765A (en) * | 2019-04-11 | 2019-07-12 | 上海星视度科技有限公司 | A kind of man-machine interaction method, device and equipment |
| CN110210284A (en) * | 2019-04-12 | 2019-09-06 | 哈工大机器人义乌人工智能研究院 | A kind of human body attitude behavior intelligent Evaluation method |
| CN110472612A (en) * | 2019-08-22 | 2019-11-19 | 海信集团有限公司 | Human bodys' response method and electronic equipment |
| CN110495889A (en) * | 2019-07-04 | 2019-11-26 | 平安科技（深圳）有限公司 | Postural assessment method, electronic device, computer equipment and storage medium |
-
2020
- 2020-05-26 CN CN202010453320.8A patent/CN111666844A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109753891A (en) * | 2018-12-19 | 2019-05-14 | 山东师范大学 | Football player's orientation calibration method and system based on human body critical point detection |
| CN109685013A (en) * | 2018-12-25 | 2019-04-26 | 上海智臻智能网络科技股份有限公司 | The detection method and device of header key point in human body attitude identification |
| 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 |
| CN110007765A (en) * | 2019-04-11 | 2019-07-12 | 上海星视度科技有限公司 | A kind of man-machine interaction method, device and equipment |
| CN110210284A (en) * | 2019-04-12 | 2019-09-06 | 哈工大机器人义乌人工智能研究院 | A kind of human body attitude behavior intelligent Evaluation method |
| CN110495889A (en) * | 2019-07-04 | 2019-11-26 | 平安科技（深圳）有限公司 | Postural assessment method, electronic device, computer equipment and storage medium |
| CN110472612A (en) * | 2019-08-22 | 2019-11-19 | 海信集团有限公司 | Human bodys' response method and electronic equipment |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112818800A (en) * | 2021-01-26 | 2021-05-18 | 中国人民解放军火箭军工程大学 | Physical exercise evaluation method and system based on human skeleton point depth image |
| CN116052273A (en) * | 2023-01-06 | 2023-05-02 | 北京体提科技有限公司 | Action comparison method and device based on body state fishbone line |
| CN116052273B (en) * | 2023-01-06 | 2024-03-08 | 北京体提科技有限公司 | Action comparison method and device based on body state fishbone line |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20190220657A1 (en) | Motion recognition device and motion recognition method | |
| CN105229666B (en) | Motion analysis in 3D images | |
| CN111666844A (en) | Badminton player motion posture assessment method | |
| US20220207921A1 (en) | Motion recognition method, storage medium, and information processing device | |
| CN109308437B (en) | Motion recognition error correction method, electronic device, and storage medium | |
| AU2020280078A1 (en) | Scoring metric for physical activity performance and training | |
| US20220222975A1 (en) | Motion recognition method, non-transitory computer-readable recording medium and information processing apparatus | |
| CN113409651A (en) | Live broadcast fitness method and system, electronic equipment and storage medium | |
| JP2018142815A (en) | Three-dimensional data acquisition device and method | |
| CN114092971A (en) | Human body action evaluation method based on visual image | |
| CN114093032A (en) | Human body action evaluation method based on action state information | |
| JP2012113438A (en) | Posture estimation apparatus and posture estimation program | |
| CN111353345B (en) | Method, apparatus, system, electronic device, and storage medium for providing training feedback | |
| CN111353347B (en) | Action recognition error correction method, electronic device, and storage medium | |
| JP7327494B2 (en) | Correction method, correction program and information processing system | |
| CN112329571A (en) | Self-adaptive human body posture optimization method based on posture quality evaluation | |
| CN114092863A (en) | Human body motion evaluation method for multi-view video image | |
| CN114092862A (en) | Action evaluation method based on optimal frame selection | |
| US11837255B2 (en) | Display method, computer-readable recording medium recording display program, and information processing apparatus | |
| CN115116087A (en) | Action assessment method, system, storage medium and electronic equipment | |
| CN110148202B (en) | Method, apparatus, device and storage medium for generating image | |
| CN112257642A (en) | Human body continuous motion similarity evaluation method and evaluation device | |
| WO2021149250A1 (en) | Exercise recognition method, exercise recognition program, and information processing device | |
| US20240144500A1 (en) | Data conversion device, moving image conversion system, data conversion method, and recording medium | |
| CN116168449A (en) | Multi-node fitness action scoring method, device and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200915 |
|
| RJ01 | Rejection of invention patent application after publication |