CN112866810B

CN112866810B - Video playing method and video playing device

Info

Publication number: CN112866810B
Application number: CN202110006378.2A
Authority: CN
Inventors: 乔乐意; 胡泊; 唐帅
Original assignee: Samsung Electronics China R&D Center; Samsung Electronics Co Ltd
Current assignee: Samsung Electronics China R&D Center; Samsung Electronics Co Ltd
Priority date: 2021-01-05
Filing date: 2021-01-05
Publication date: 2023-04-21
Anticipated expiration: 2041-01-05
Also published as: CN112866810A

Abstract

A video playing method and a video playing device are provided. The video playing method comprises the following steps: acquiring actions of a user in real time; when the action of the user is acquired, calculating the matching degree of the action of the user and the action corresponding to the action of the user in the video; and when the matching degree is greater than a predetermined value, adjusting the playing position of the video based on more than one of the action speed of the user, the action accuracy of the user and the change rate of actions in the video. According to the video playing method and the video playing device, the playing position of the video can be dynamically adjusted to play according to the real-time action of the user, so that the video playing progress can be matched with the action rhythm of the user, the user is prevented from manually adjusting the playing position, the user is enabled to better focus on the exercise of the action, and the user experience is greatly improved.

Description

Video playing method and video playing device

Technical Field

The present disclosure relates to the field of electronic technologies, and in particular, to a video playing method and a video playing device.

Background

With the importance of people on health, more and more people use electronic devices such as mobile phones, tablet computers, televisions and the like to learn various exercises at any time and any place. At present, the learning of various sports is mainly performed by a user along with a sports teaching video, however, because the video playing speed is unchanged, when complex actions are encountered or various actions in the video are switched, the situation that the user cannot keep pace with or the actions are not right is often caused, in this case, the user can only stop the current actions, and pause, fast forward, fast backward and the like are manually performed to adjust the video to a desired playing position, which is time-consuming and labor-consuming. Although there is currently also a problem such as Keep that the whole video process is divided into segments to improve the user experience to some extent, there is no fundamental improvement but a problem of managing a plurality of segments.

Disclosure of Invention

An object of an exemplary embodiment of the present disclosure is to provide a video playing method and a video playing device, so that a playing position of a video can be dynamically adjusted to play according to a real-time action of a user, so that a video playing progress can be matched with an action rhythm of the user, the user is prevented from manually adjusting the playing position, the user is better focused on practice of the action, and user experience is greatly improved.

An aspect of exemplary embodiments of the present disclosure provides a video playing method, including: acquiring actions of a user in real time; when the action of the user is acquired, calculating the matching degree of the action of the user and the action corresponding to the action of the user in the video; and when the matching degree is greater than a predetermined value, adjusting the playing position of the video based on more than one of the action speed of the user, the action accuracy of the user and the change rate of actions in the video.

Optionally, the video playing method further includes: and when the matching degree is smaller than or equal to a preset value, not adjusting the playing position of the video, and stopping playing the video when a preset condition is met.

Optionally, the predetermined condition includes: the number of times that the degree of matching is continuously less than or equal to a predetermined value reaches a predetermined number of times, and the state that the degree of matching is less than or equal to the predetermined value continues for a first predetermined time.

Optionally, the video playing method further includes: and when the action of the user cannot be acquired, suspending playing the video.

Optionally, the video playing method further includes: and determining the playing position of the video selected by the user and starting to play the video from the playing position.

Optionally, the step of determining the playing position of the video selected by the user includes: a play position of the user-selected video is determined based on the play position selection action of the user.

Optionally, the step of determining the play position of the video selected by the user based on the play position selection action of the user comprises: acquiring a play position selection action of the user; and when a video segment uniquely matched with the play position selection action exists in the video, determining an n+1st action after the video segment uniquely matched with the play position selection action in the video as the play position, wherein n is a position adjustment amount and is a natural number greater than or equal to 1, and the play position selection action comprises more than one continuous action.

Optionally, the step of determining the play position of the video selected by the user based on the play position selection action of the user further comprises: and in response to the fact that a plurality of video segments matched with the current play position selection action exist in the video, enabling the user to increase the number of actions in the current play position selection action to continue matching, and determining an n+1th action after a video segment with highest total matching degree in the plurality of video segments matched with the current play position selection action in the video as the play position when the total matching time reaches a second preset time, or determining an n+1th action after a first video segment in the plurality of video segments matched with the current play position selection action in the video as the play position.

Optionally, in response to an initial action of the user, the step of determining a play position of the video selected by the user is performed.

Optionally, in response to the user's initiation, prompting the user to select a play position of the video, and performing the step of determining the play position of the video selected by the user.

Optionally, the video playing method further includes: and responding to the ending action of the user, and ending the playing of the video.

Optionally, the step of adjusting the playing position of the video includes: when the matching degree is larger than a preset value, judging whether more than one action with the change rate of 0 between actions corresponding to the actions of the user exist continuously after the actions corresponding to the actions of the user in the video; and determining whether to adjust the playing position of the video based on the judging result.

Optionally, the step of determining whether to adjust the playing position of the video based on the determination result includes: determining not to adjust the playing position of the video when the judging result indicates that more than one action with the change rate of the actions corresponding to the actions of the user is 0 continuously exists, and suspending playing the video when the video is played to the action with the change rate of the actions corresponding to the actions of the user not being 0; and when the judgment result indicates that more than one action with the change rate of actions corresponding to the actions of the user is 0 is discontinuous, determining to adjust the playing position of the video based on more than one of the action speed of the user, the action accuracy of the user and the change rate of the actions in the video.

Optionally, the step of adjusting the playing position of the video based on more than one of the action speed of the user, the action accuracy of the user, and the rate of change of the actions in the video comprises: adjusting a position adjustment amount based on one or more of a motion speed of the user, a motion accuracy of the user, and a rate of change of motion in the video; and obtaining a play position of the video based on the position of the action corresponding to the action of the user in the video and the position adjustment amount.

Alternatively, when the position adjustment amount is adjusted based on the movement speed of the user, the position adjustment amount is decreased if the movement speed is slow, and the position adjustment amount is increased if the movement speed is fast.

Alternatively, when the position adjustment amount is adjusted based on the motion accuracy of the user, the position adjustment amount is increased if the motion accuracy is increased, and the position adjustment amount is decreased if the motion accuracy is decreased.

Optionally, when adjusting the position adjustment amount based on a rate of change of an action in the video, the position adjustment amount is decreased if the rate of change increases, and the position adjustment amount is increased if the rate of change decreases.

Optionally, the position adjustment amount is adjusted by weighting when the position adjustment amount is adjusted based on two or more of the speed of action of the user, the accuracy of action of the user, and the rate of change of action in the video.

Optionally, the action of the user is obtained as a recognition unit, one recognition unit representing one action, the recognition unit comprising a plurality of frames and comprising at least one key frame.

Optionally, the action corresponding to the action of the user in the video is represented as a video unit, the video unit is obtained by dividing the video according to the action, and the video unit includes a plurality of frames and includes at least one key frame.

Another aspect of exemplary embodiments of the present disclosure provides a video playing device including: an action acquisition unit configured to acquire an action of a user in real time; a matching degree calculating unit configured to calculate, when an action of the user is acquired, a matching degree of the action of the user and an action corresponding to the action of the user in the video; and a play position adjustment unit configured to adjust a play position of the video based on one or more of a motion speed of the user, a motion accuracy of the user, and a rate of change of motion in the video when the matching degree is greater than a predetermined value.

Optionally, the play position adjustment unit is configured to not adjust the play position of the video when the matching degree is less than or equal to a predetermined value, and to pause playing the video when a predetermined condition is satisfied.

Optionally, the play position adjustment unit is configured to pause playing the video when the action of the user cannot be acquired by the action acquisition unit.

Optionally, the video playing device further includes: a play position determining unit configured to determine a play position of the video selected by the user to start playing the video from the play position.

Optionally, the play position determining unit is configured to determine the play position of the video selected by the user based on a play position selection action of the user.

Optionally, the play position determining unit is configured to: acquiring a play position selection action of the user; and when a video segment uniquely matched with the play position selection action exists in the video, determining an n+1st action after the video segment uniquely matched with the play position selection action in the video as the play position, wherein n is a position adjustment amount and is a natural number greater than or equal to 1, and the play position selection action comprises more than one continuous action.

Optionally, the play position determining unit is further configured to: and in response to the fact that a plurality of video segments matched with the current play position selection action exist in the video, enabling the user to increase the number of actions in the current play position selection action to continue matching, and determining an n+1th action after a video segment with highest total matching degree in the plurality of video segments matched with the current play position selection action in the video as the play position when the total matching time reaches a second preset time, or determining an n+1th action after a first video segment in the plurality of video segments matched with the current play position selection action in the video as the play position.

Optionally, the play position determining unit is configured to determine the play position of the video selected by the user in response to an initial action of the user.

Optionally, the play position determining unit is configured to prompt the user to select a play position of the video in response to the user's start action, and determine the play position of the video selected by the user.

Optionally, the video playing device further includes: and the playing ending unit responds to the ending action of the user and ends the playing of the video.

Optionally, the play position adjustment unit is configured to determine whether there is more than one motion with a rate of change of 0 between motions corresponding to the motions of the user continuously after the motion corresponding to the motions of the user in the video when the matching degree is greater than a predetermined value; and determining whether to adjust the playing position of the video based on the judging result.

Optionally, the play position adjustment unit is further configured to: determining not to adjust the playing position of the video when the judging result indicates that more than one action with the change rate of the actions corresponding to the actions of the user is 0 continuously exists, and suspending playing the video when the video is played to the action with the change rate of the actions corresponding to the actions of the user not being 0; and when the judgment result indicates that more than one action with the change rate of actions corresponding to the actions of the user is 0 is discontinuous, determining to adjust the playing position of the video based on more than one of the action speed of the user, the action accuracy of the user and the change rate of the actions in the video.

Optionally, the play position adjustment unit is configured to: adjusting a position adjustment amount based on one or more of a motion speed of the user, a motion accuracy of the user, and a rate of change of motion in the video; and obtaining a play position of the video based on the position of the action corresponding to the action of the user in the video and the position adjustment amount.

Optionally, the play position adjustment unit is configured to, when adjusting the position adjustment amount based on the action speed of the user, decrease the position adjustment amount if the action speed is slow, and increase the position adjustment amount if the action speed is fast.

Optionally, the play position adjustment unit is configured to increase the position adjustment amount if the motion accuracy increases and decrease the position adjustment amount if the motion accuracy decreases when adjusting the position adjustment amount based on the motion accuracy of the user.

Optionally, the play position adjustment unit is configured to, when adjusting the position adjustment amount based on a rate of change of an action in the video, decrease the position adjustment amount if the rate of change increases, and increase the position adjustment amount if the rate of change decreases.

Optionally, the play position adjustment unit is configured to adjust the position adjustment amount by weighting when adjusting the position adjustment amount based on two or more of a speed of motion of the user, an accuracy of motion of the user, and a rate of change of motion in the video.

Another aspect of exemplary embodiments of the present disclosure provides a computer-readable storage medium storing a computer program, which when executed by a processor, implements the video playback method of any one of the above.

Another aspect of exemplary embodiments of the present disclosure provides a computing device, the computing device comprising: a processor; a memory storing a computer program which, when executed by the processor, implements the video playback method of any one of the above.

According to the video playing method and the video playing device, the playing position of the video can be dynamically adjusted to play according to the real-time action of the user, so that the video playing progress can be matched with the action rhythm of the user, the user is prevented from manually adjusting the playing position, the user is enabled to better concentrate on the exercise of the action, and the user experience is greatly improved.

Additional aspects and/or advantages of the disclosure will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the disclosure.

Drawings

The foregoing and/or other objects and advantages of the disclosure will become more apparent from the following description of embodiments taken in conjunction with the accompanying drawings in which:

fig. 1 is a flowchart illustrating a video playing method according to an exemplary embodiment of the present disclosure;

FIG. 2 is a flowchart illustrating a method of determining a play position of a video selected by a user according to an exemplary embodiment of the present disclosure;

fig. 3 is a schematic diagram illustrating an identification unit according to an exemplary embodiment of the present disclosure;

fig. 4 is a block diagram illustrating a video playback device according to an exemplary embodiment of the present disclosure.

Detailed Description

Reference will now be made in detail to the exemplary embodiments of the present disclosure, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to like elements throughout. The embodiments will be described below in order to explain the present disclosure by referring to the figures. In the following, a scene in which a user exercises sports following a sports teaching video will be described as an example. Here, the user sequentially makes actions in the order of actions in the motion picture.

Fig. 1 is a flowchart illustrating a video playing method according to an exemplary embodiment of the present disclosure. The method may be implemented by a computer program. For example, the video playing method may be implemented by executing the program in an electronic terminal, such as a smart phone, a tablet computer, a computer, or the like.

As shown in fig. 1, in step S101, the action of the user is acquired in real time. That is, in the process of playing video, the actions of the user are acquired in real time while the user makes the actions. The action may be a static action or a dynamic action. Here, the user's actions may be acquired in real time through various methods. For example, a user may be photographed with a multi-azimuth camera and the user's actions acquired in real-time in conjunction with a motion capture algorithm. As an example, the user's action may be obtained as an identification unit, i.e. an identification unit is obtained as the user's action. Specifically, video data obtained by photographing a user is sequentially acquired as recognition units by action, one recognition unit representing each action. Fig. 3 is a schematic diagram illustrating an identification unit according to an exemplary embodiment of the present disclosure. As shown in fig. 3, the identification unit may include a plurality of frames (frame data), and the identification unit includes at least one key frame. The motion information of the user can be obtained by performing weighting processing on each frame included in the identification means.

In the exemplary embodiments of the present disclosure, by acquiring the action of the user as the recognition unit, efficiency and accuracy can be greatly improved compared to the case where the action of the user is acquired in units of frames.

In step S102, it is determined whether or not an action of the user is acquired. When the motion of the user is acquired, step S103 is executed to calculate the matching degree between the motion of the user and the motion corresponding to the motion of the user in the video. Here, the matching degree between the motion of the user and the motion corresponding to the motion of the user in the video is the similarity between the motion of the user and the motion corresponding to the motion of the user in the video. The degree of matching may be calculated by various methods existing. In addition, as an example, in a case where the action of the user is acquired as the recognition unit, accordingly, the action corresponding to the action of the user in the video is expressed as a video unit. The video unit is obtained by dividing videos according to actions. That is, one video unit represents one action in the video. Furthermore, the video unit, like the identification unit, may comprise a plurality of frames and contain at least one key frame. In this way, the result obtained by calculating the matching degree between the motion of the user and the motion corresponding to the motion of the user in the video is more accurate.

When step S102 determines that the user' S motion cannot be acquired, for example, when the user temporarily leaves, step S108 is executed to pause the video. The state of suspending playing of the video is released according to the fact that the action of the user is acquired and the matching degree of the action of the user and the action corresponding to the action of the user in the video is larger than a preset value.

In step S104, it is determined whether the degree of matching is greater than a predetermined value. Here, the predetermined value is a value capable of determining that the motion of the user matches the motion corresponding to the motion of the user in the video. The predetermined value may be determined by various methods, for example, may be determined experimentally, or may be determined by theoretical calculation. When the matching degree is greater than a predetermined value, step S105 is executed to adjust the play position of the video based on one or more of the motion speed of the user, the motion accuracy of the user, and the rate of change of the motion in the video.

Specifically, the step of adjusting the play position of the video based on one or more of the motion speed of the user, the motion accuracy of the user, and the rate of change of the motion in the video may include: the position adjustment amount is adjusted based on one or more of the user's motion speed, the user's motion accuracy, and the rate of change of motion in the video. The position adjustment amount is a variable for dynamically adjusting the play position of the video. The position adjustment amount may be adjusted each time it is determined that the degree of matching is greater than a predetermined value to adjust the play position of the video. However, the present disclosure is not limited thereto, and the number and timing of adjustment of the position adjustment amount may be appropriately changed according to the needs of the user. The position adjustment amount is given an initial value when the user starts playing the teaching video. The initial value may be a value obtained according to the past practice situation of the user. The initial value is determined, for example, based on the degree of overall matching (accuracy) and proficiency of the user's previous practice. In addition, the action speed of the user may be represented by the duration of time the user completes the action. As one example, this may be represented by a time period of the identification unit, but the present disclosure is not limited thereto. The action accuracy of the user can be represented by the matching degree of the action of the user and the action corresponding to the action of the user in the video. As one example, this may be represented by a degree of matching between the recognition unit and the corresponding video unit, but the present disclosure is not limited thereto. Also, the rate of change of an action in the video may be represented by the rate of change between two adjacent actions (video units).

As one example, when the position adjustment amount is adjusted based on the movement speed of the user, the position adjustment amount is decreased if the movement speed is slow, and the position adjustment amount is increased if the movement speed is fast. Here, the user's action speed may be reduced or increased by comparing the difference between the time periods of the currently acquired user's action and the corresponding action in the video and the time period of the previously acquired user's action and the corresponding action in the video, but may be obtained by other methods. When the position adjustment amount is adjusted based on the motion accuracy of the user, the position adjustment amount is increased if the motion accuracy is increased, and the position adjustment amount is decreased if the motion accuracy is decreased. Here, the increase or decrease in the action accuracy of the user may be obtained by comparing the matching degree of the action of the user currently acquired with the matching degree of the action of the user previously acquired, but may be obtained by other methods. When the position adjustment amount is adjusted based on the rate of change of the motion in the video, the position adjustment amount is decreased if the rate of change is increased, and the position adjustment amount is increased if the rate of change is decreased. Here, the increase or decrease in the rate of change of the motion in the video may be a change in the rate of change between the motion currently corresponding to the motion of the user and the motion immediately preceding the motion with respect to the rate of change between two adjacent motions preceding the corresponding motion, and may be obtained by other methods. In addition, when the position adjustment amount is adjusted based on two or more of the user's motion speed, the user's motion accuracy, and the rate of change of motion in the video, the position adjustment amount is adjusted by weighting. In this way, the adjustment can be performed in real time according to the situation of the user's action exercise. In addition, by weighting two or more of the motion speed of the user, the motion accuracy of the user, and the rate of change of motion in the video, the video can be adjusted with priority given to a certain aspect, and further, the video play position can be adjusted more humanizedly.

In step S105, after the position adjustment amount is adjusted, the method further includes: and obtaining the playing position of the video based on the position of the action corresponding to the action of the user in the video and the position adjustment amount. Thereby, the play position of the video is adjusted by the position adjustment amount. As an example, the play position of the video may be adjusted to a position of an xth action after the position of the action corresponding to the acquired action of the user. Here, x represents a position adjustment amount. That is, when the motion corresponding to the acquired motion of the user is the y-th video unit, the play position of the video is adjusted to the y+x-th video unit. And x and y are natural numbers greater than or equal to 1.

It should be understood that, the position adjustment amount x is updated when the matching degree is greater than the predetermined value, and then the playing position of the video is adjusted based on the updated position adjustment amount x, and the video is played from the adjusted playing position after the playing of the current playing action (i.e. the video unit) is completed.

Therefore, according to the video playing method of the exemplary embodiment of the disclosure, the playing position of the video can be dynamically adjusted to play according to the real-time action of the user, so that the video playing progress can be matched with the action rhythm of the user, the user is prevented from manually adjusting the playing position, the user is enabled to better concentrate on the exercise of the action, and the user experience is greatly improved.

As an example, the step of adjusting the playing position of the video includes: when the matching degree is larger than a preset value, judging whether more than one action with the change rate of 0 between actions corresponding to the actions of the user exist continuously after the actions corresponding to the actions of the user in the video. That is, it is determined whether or not an action corresponding to the action of the user is followed by an action identical to the action in the video. In other words, it is determined whether or not an action corresponding to the action of the user continuously repeatedly appears. It should be noted that whether or not the action subsequent to the action corresponding to the action of the user is identical to the action can be determined by various conventional methods. Then, whether to adjust the playing position of the video is determined based on the judging result. Specifically, when the determination result indicates that there is more than one motion with a rate of change of motion between motions corresponding to the motion of the user being 0 in succession, it is determined that the play position of the video is not adjusted, and when the motion with a rate of change of motion between the motions being 0 in succession is played, the play of the video is paused. Here, not adjusting the playing position of the video means that the backward playing is continued according to the current playing progress. That is, when the actions corresponding to the actions of the user are continuously repeated, the same actions are repeated, and therefore, even if the play position of the video is not adjusted, the user knows the action key of the next action, and the situation of not keeping pace with the user does not occur. Further, since the play position of the video is not adjusted, the play speed of the video may be faster than the action speed of the user, and thus, when the video is played to an action different from the same action continuously existing, the video is paused to wait. When the determination result indicates that there is not more than one motion with a motion rate of 0 between the motions corresponding to the motions of the user, the play position of the video is determined to be adjusted based on one or more of the motion speed of the user, the motion accuracy of the user, and the motion rate of the video. That is, when the motions in the videos are different from each other, as described above, the play position of the video needs to be adjusted based on one or more of the motion speed of the user, the motion accuracy of the user, and the rate of change of the motions in the video, so that the user can keep pace with the user. A specific method for adjusting the play position of the video is as described above.

In addition, when step S104 determines that the matching degree is less than or equal to a predetermined value, step S106 is performed without adjusting the play position of the video. That is, when the motion of the user does not match the motion corresponding to the motion of the user in the video, continuing to play backward according to the current play progress. As one example, not adjusting the play position of the video refers to not adjusting the position adjustment amount. Then, in step S107, it is determined whether a predetermined condition is satisfied. As one example, the predetermined condition includes: the number of times that the degree of matching is continuously less than or equal to a predetermined value reaches a predetermined number of times, and the state that the degree of matching is less than or equal to the predetermined value continues for a first predetermined time. When the predetermined condition is satisfied, step S108 is performed to pause playing of the video. That is, when the motion of the user is continuously mismatched with the motion corresponding to the motion of the user in the video for a predetermined number of times or for a first predetermined time, the playing of the video is paused. Here, the predetermined number of times and the first predetermined time may be arbitrarily set, may be set according to the action practice habit of the user, and may be set by other means than the predetermined number of times and the first predetermined time. The state of suspending playing of the video is released according to the matching of the acquired action of the user and the action corresponding to the action of the user in the video. When it is determined in step S107 that the predetermined condition is not satisfied, the routine returns to step S106, i.e., the video is played without adjusting the play position until the predetermined condition is satisfied.

Therefore, when the actions of the user are not matched, the user can continuously try a certain number of times or a certain time, the playing position is not adjusted at the moment, the video is normally played, the video is paused in the condition that the actions are not matched after the preset number of times or the first preset time is reached, the user can continuously and singly exercise the actions in the time of pausing the playing, and when the action exercise is accurate and matched with the corresponding actions in the video, the playing position of the video is adjusted to play. Therefore, the jump playing is avoided by adjusting the playing position when the actions of the users are not matched each time, and smooth experience is provided for the users.

In the video playing method according to the exemplary embodiment of the present disclosure, when it is determined that the video playing method is matched with the video playing method, a prompt tone may be given or a prompt screen may be displayed to the user so that the user may learn about the exercise condition of the user.

In an exemplary embodiment of the present disclosure, the video playing method may further include a step of determining a playing position of the video selected by the user to start playing the video from the playing position, before step S101. Here, the user can select a play position of the video in various existing manners. As one example, a user may select a play location of a video by taking an action of a location in the video that is desired to be played. That is, the step of determining the play position of the video selected by the user includes: a play position of the user-selected video is determined based on the play position selection action of the user.

In particular, fig. 2 is a flowchart illustrating a method of determining a play position of a video selected by a user according to an exemplary embodiment of the present disclosure.

As shown in fig. 2, in step S201, a play position selection action of the user is acquired. Here, the user may take any one of the actions in the video or the continuous action in any one of the video segments as the play position selection action. The method of obtaining the play position selection action of the user is as described above. For example, a user may be photographed with a multi-azimuth camera and a play position selection action of the user may be obtained in conjunction with a motion capture algorithm. As one example, the play position selection action of the user includes more than one continuous action. When the play position selection action of the user is acquired, first, one action of the user is acquired as the play position selection action. Then, step S202 is executed to determine whether there is a video segment in the video that is uniquely matched with the play position selection action. When there is a video segment in the video that is uniquely matched with the play position selection action, step S203 is executed to determine an n+1st action after the video segment in the video that is uniquely matched with the play position selection action as the play position. Here, n is a position adjustment amount, and n is a natural number greater than or equal to 1. That is, when there is a video segment in the video that uniquely matches the play position selection action, the play position is determined based on the position of the video segment and the position adjustment amount. For example, assuming that the play position selection action is uniquely matched with a video segment in a video, such as an mth video unit, and the current position adjustment amount is n, the determined play position is the mth+n+1th video unit.

In exemplary embodiments of the present disclosure, whether there is a unique match may be determined by various existing matching algorithms (e.g., direct search, BM algorithm, KMP algorithm, etc.).

When it is determined in step S202 that there are a plurality of video segments matching the play position selection action in the video, in response to the presence of a plurality of video segments matching the current play position selection action (including one action) in the video, step S204 is executed to cause the user to increase the number of actions in the current play position selection action and continue the matching. I.e. the user is prompted to further act to make a unique match. Here, the user may be prompted to further act by voice or a screen. The play position selection operation is gradually increased one by one after one operation is determined to be a non-unique match. Then, step S205 is executed to continue to acquire the play position selection action of the user. At this time, the play position selection action includes two continuous actions. When the play position selection action of the user is further acquired, step S206 is executed to determine whether a video segment uniquely matching the current play position selection action exists in the video. When there is a video segment in the video that is uniquely matched with the current play position selection action, step S203 is executed to determine an n+1th action after the video segment in the video that is uniquely matched with the current play position selection action as the play position. For example, assuming that the current play position selection action (including two consecutive actions) uniquely matches actions in the video, such as the mth video unit and the (m+1) th video unit, the determined play position is the (m+1+n+1) th video unit.

Thus, when there is a video segment in the video that uniquely matches the play position selection action, the determined play position is located at the n+1th action after the video segment that uniquely matches the play position selection action.

On the other hand, when it is determined in step S206 that there are a plurality of video segments in the video that match the current play position selection action, step S207 is executed to determine whether the total matching time reaches a second predetermined time. Here, the total matching time is a time from the first matching to the current matching. The second predetermined time may be arbitrarily set, for example, may be set to 10s or the like. When the total matching time reaches the second predetermined time, step S208 is executed to determine, as the playing position, an n+1th action after a video segment having the highest total matching degree among the plurality of video segments matching the current playing position selecting action in the video, or determine, as the playing position, an n+1th action after a first video segment among the plurality of video segments matching the current playing position selecting action in the video. That is, when the total matching time reaches the second predetermined time, the play position is determined based on the position and the position adjustment amount of the video segment having the highest total matching degree among the plurality of video segments, or based on the position and the position adjustment amount of the first video segment among the plurality of video segments. For example, assuming that the current play position selection action (including two actions) matches actions in video such as the mth and m+1th video units, the mth+8th and m+9th video units, the matching degree with the mth and m+1th video units is 78% and 78%, respectively, and the matching degree with the mth+8th and m+9th video units is 85% and 74%, respectively, when the total matching time reaches the second predetermined time, that is, when the total matching time is over, the determined play position is the (n+1) th action after the video segment having the highest total matching degree, that is, the (m+9+n+1) th video unit, or is the (n+1) th action after the first video segment of the two video segments, that is, the (m+1+n+1) th video unit.

When it is determined in step S207 that the total matching time has not reached the second predetermined time, the routine returns to step S204 to increase the number of actions in the current play position selection action. I.e. the user is prompted to further act to make a unique match.

After determining the play position of the video, the user may be notified by an alert tone or an alert screen, and then the step S101 in fig. 1 is started to be executed, and the user' S action is acquired in real time. Since the user follows the video to exercise the sport motion, the motion performed by the user after the play position selection motion is a subsequent motion of the motion matching the play position selection motion in the video. For example, when it is determined that the play position of the video is the m+1+n+1-th video unit (i.e., the m+2+n-th video unit), the action (recognition unit) of the user acquired in real time corresponds to the m+2-th video unit in the video, that is, the action performed by the user after the play position selection action (the m-th video unit and the m+1-th video unit) is the action corresponding to the m+2-th video unit in the video.

As one example, the video playing method of the exemplary embodiment of the present disclosure may perform the step of determining a playing position of the video selected by the user in response to the user's initial motion. Here, the initial motion is a motion indicating that the user starts to perform motion exercise, and may be a static motion or a dynamic motion. As an example, the initiating action may be obtained as an identification unit. In addition, the initiation action may be a user-defined action or an action intercepted from the video, but the disclosure is not limited thereto. For example, in the scenario where the user exercises fancy basketball, the user holding action may be taken as the initiating action.

As an example, the video playing method of the exemplary embodiment of the present disclosure may further prompt the user to select a playing position of the video in response to the user's start action, and then perform the step of determining the playing position of the video selected by the user. Here, the user may be prompted to select a play position of the video by voice or a screen.

As an example, the video playing method of the exemplary embodiment of the present disclosure may further end the playing of the video in response to the ending action of the user. Here, the ending motion is a motion indicating that the user ends the motion exercise, and may be a static motion or a dynamic motion. As an example, the ending action may be obtained as one recognition unit. In addition, the ending action may be a user-defined action or an action intercepted from the video, but the disclosure is not limited thereto. For example, in a case where the user exercises fancy basketball, the user holding action may be set as the ending action.

In the exemplary embodiment of the present disclosure, the matching degree, the duration, the start time and the end time of each motion of the user in the video of each exercise of the user may be collected during the process that the user follows the motion of the video exercise motion, so that the total matching degree (accuracy) and proficiency of each exercise of the user may be calculated. The total matching degree can be calculated by averaging the matching degree of each action, or can be obtained by using a weighted average value. The higher the total match value, the higher the accuracy of the user exercise. Proficiency may be obtained by adding the duration of each action of the user and then dividing by the total duration of the exercise action in the video (end time-start time in the video). The smaller the value of proficiency, the higher the proficiency the user exercises. Thus, the exercise characteristic curve of the user can be obtained, and the position adjustment amount and the initial value thereof can be better adjusted to adapt to the exercise of the user. In addition, the position where the video starts to be played can be determined based on the accuracy, proficiency and practice habit of the user in the past practice. For example, when there are a plurality of video segments that match, the weight of the position that the user has frequently selected before may be increased to determine the position at which the video starts to play.

As shown in fig. 4, the video playback apparatus includes: action acquisition unit 100, matching degree calculation unit 200, and play position adjustment unit 300.

Wherein the action acquisition unit 100 is configured to acquire the action of the user in real time. That is, in the process of playing video, the actions of the user are acquired in real time while the user makes the actions. The action may be a static action or a dynamic action. Here, the user's actions may be acquired in real time through various methods. For example, a user may be photographed with a multi-azimuth camera and the user's actions acquired in real-time in conjunction with a motion capture algorithm. As an example, the user's action may be obtained as an identification unit, i.e. an identification unit is obtained as the user's action. Specifically, video data obtained by photographing a user is sequentially acquired as recognition units by action, one recognition unit representing each action. As shown in fig. 3, the identification unit may include a plurality of frames (frame data), and the identification unit includes at least one key frame. The motion information of the user can be obtained by performing weighting processing on each frame included in the identification means.

The matching degree calculating unit 200 is configured to calculate, when the motion of the user is acquired by the motion acquiring unit 100, a matching degree of the motion of the user with the motion corresponding to the motion of the user in the video. Here, the matching degree between the motion of the user and the motion corresponding to the motion of the user in the video is the similarity between the motion of the user and the motion corresponding to the motion of the user in the video. The degree of matching may be calculated by various methods existing. In addition, as an example, in a case where the action of the user is acquired as the recognition unit, accordingly, the action corresponding to the action of the user in the video is expressed as a video unit. The video unit is obtained by dividing videos according to actions. That is, one video unit represents one action in the video. Furthermore, the video unit may comprise a plurality of frames, and contain at least one key frame, as the identification unit. In this way, the result obtained by calculating the matching degree between the motion of the user and the motion corresponding to the motion of the user in the video is more accurate.

In addition, when the action acquisition unit 100 cannot acquire the action of the user, for example, when the user temporarily leaves, the play position adjustment unit 300 described later may pause playing the video. The state of suspending playing of the video is released according to the fact that the action of the user is acquired and the matching degree of the action of the user and the action corresponding to the action of the user in the video is larger than a preset value.

The play position adjustment unit 300 is configured to adjust a play position of the video based on one or more of a motion speed of the user, a motion accuracy of the user, and a rate of change of motion in the video when the matching degree calculated by the matching degree calculation unit 200 is greater than a predetermined value. Here, the predetermined value is a value capable of determining that the motion of the user matches the motion corresponding to the motion of the user in the video. The predetermined value may be determined by various methods, for example, may be determined experimentally, or may be determined by theoretical calculation.

Specifically, the play position adjustment unit 300 may be configured to: the position adjustment amount is adjusted based on one or more of the user's motion speed, the user's motion accuracy, and the rate of change of motion in the video. The position adjustment amount is a variable for dynamically adjusting the play position of the video. The position adjustment amount may be adjusted each time it is determined that the degree of matching is greater than a predetermined value to adjust the play position of the video. However, the present disclosure is not limited thereto, and the number and timing of adjustment of the position adjustment amount may be appropriately changed according to the needs of the user. The position adjustment amount is given an initial value when the user starts playing the teaching video. The initial value may be a value obtained according to the past practice situation of the user. The initial value is determined, for example, based on the degree of overall matching (accuracy) and proficiency of the user's previous practice. In addition, the action speed of the user may be represented by the duration of time the user completes the action. As one example, this may be represented by a time period of the identification unit, but the present disclosure is not limited thereto. The action accuracy of the user can be represented by the matching degree of the action of the user and the action corresponding to the action of the user in the video. As one example, this may be represented by a degree of matching between the recognition unit and the corresponding video unit, but the present disclosure is not limited thereto. Also, the rate of change of an action in the video may be represented by the rate of change between two adjacent actions (video units).

As one example, the play position adjustment unit 300 may be configured to, when adjusting the position adjustment amount based on the action speed of the user, decrease the position adjustment amount if the action speed is slow, and increase the position adjustment amount if the action speed is fast. Here, the user's action speed may be reduced or increased by comparing the difference between the time periods of the currently acquired user's action and the corresponding action in the video and the time period of the previously acquired user's action and the corresponding action in the video, but may be obtained by other methods. Also, the play position adjustment unit 300 may be configured to increase the position adjustment amount if the motion accuracy increases and decrease the position adjustment amount if the motion accuracy decreases when the position adjustment amount is adjusted based on the motion accuracy of the user. Here, the increase or decrease in the action accuracy of the user may be obtained by comparing the matching degree of the action of the user currently acquired with the matching degree of the action of the user previously acquired, but may be obtained by other methods. The play position adjustment unit 300 may be configured to, when adjusting the position adjustment amount based on a rate of change of an action in the video, decrease the position adjustment amount if the rate of change increases, and increase the position adjustment amount if the rate of change decreases. Here, the increase or decrease in the rate of change of the motion in the video may be a change in the rate of change between the motion currently corresponding to the motion of the user and the motion immediately preceding the motion with respect to the rate of change between two adjacent motions preceding the corresponding motion, and may be obtained by other methods. In addition, when the position adjustment amount is adjusted based on two or more of the user's motion speed, the user's motion accuracy, and the rate of change of motion in the video, the position adjustment amount is adjusted by weighting. In this way, the adjustment can be performed in real time according to the situation of the user's action exercise. In addition, by weighting two or more of the motion speed of the user, the motion accuracy of the user, and the rate of change of motion in the video, the video can be adjusted with priority given to a certain aspect, and further, the video play position can be adjusted more humanizedly.

After the position adjustment amount is adjusted as described above, the play position adjustment unit 300 may obtain the play position of the video based on the position of the action corresponding to the action of the user in the video and the position adjustment amount. Thereby, the play position of the video is adjusted by the position adjustment amount. As an example, the play position of the video may be adjusted to a position of an xth action after the position of the action corresponding to the acquired action of the user. Here, x represents a position adjustment amount. That is, when the motion corresponding to the acquired motion of the user is the y-th video unit, the play position of the video is adjusted to the y+x-th video unit. And x and y are natural numbers greater than or equal to 1.

Therefore, according to the video playing device of the exemplary embodiment of the disclosure, the playing position of the video can be dynamically adjusted to play according to the real-time action of the user, so that the video playing progress can be matched with the action rhythm of the user, the user is saved from manually adjusting the playing position, the user is better focused on the exercise of the action, and the user experience is greatly improved.

As one example, the play position adjustment unit 300 may be configured to determine whether there is one or more actions in the video corresponding to the actions of the user that are followed by an action with a change rate of 0 between the actions corresponding to the actions of the user when the matching degree is greater than a predetermined value. That is, it is determined whether or not an action corresponding to the action of the user is followed by an action identical to the action in the video. In other words, it is determined whether or not an action corresponding to the action of the user continuously repeatedly appears. It should be noted that whether or not the action subsequent to the action corresponding to the action of the user is identical to the action can be determined by various conventional methods. Then, whether to adjust the playing position of the video is determined based on the judging result. Specifically, the play position adjustment unit 300 may be further configured to: and when the judging result indicates that more than one action with the change rate of the action between the actions corresponding to the actions of the user is continuously present and is 0, determining that the playing position of the video is not adjusted, and stopping playing the video when the action with the change rate of the action between the actions is continuously present and is not 0 is played. Here, not adjusting the playing position of the video means that the backward playing is continued according to the current playing progress. That is, when the actions corresponding to the actions of the user are continuously repeated, the same actions are repeated, and therefore, even if the play position of the video is not adjusted, the user knows the action key of the next action, and the situation of not keeping pace with the user does not occur. Further, since the play position of the video is not adjusted, the play speed of the video may be faster than the action speed of the user, and thus, when the video is played to an action different from the same action continuously existing, the video is paused to wait. When the determination result indicates that there is not more than one motion with a motion rate of 0 between the motions corresponding to the motions of the user, the play position of the video is determined to be adjusted based on one or more of the motion speed of the user, the motion accuracy of the user, and the motion rate of the video. That is, when the motions in the videos are different from each other, as described above, the play position of the video needs to be adjusted based on one or more of the motion speed of the user, the motion accuracy of the user, and the rate of change of the motions in the video, so that the user can keep pace with the user. A specific method for adjusting the play position of the video is as described above.

On the other hand, when the matching degree is less than or equal to the predetermined value, the play position adjustment unit 300 does not adjust the play position of the video (i.e., continues the backward play at the current play progress), and pauses the play of the video when a predetermined condition is satisfied. As one example, not adjusting the play position of the video refers to not adjusting the position adjustment amount. Further, the predetermined condition may include: the number of times that the degree of matching is continuously less than or equal to a predetermined value reaches a predetermined number of times, and the state that the degree of matching is less than or equal to the predetermined value continues for a first predetermined time. That is, when the motion of the user is continuously mismatched with the motion corresponding to the motion of the user in the video for a predetermined number of times or for a first predetermined time, the playing of the video is paused. Here, the predetermined number of times and the first predetermined time may be arbitrarily set, may be set according to the action practice habit of the user, and may be set by other means than the predetermined number of times and the first predetermined time. The state of suspending playing of the video is released according to the matching of the acquired action of the user and the action corresponding to the action of the user in the video.

It should be noted that, the video playing device of the exemplary embodiment of the present disclosure may send out a prompt tone or display a prompt screen to the user when the video playing device is matched with the video playing device and the video playing device is not matched with the video playing device, so that the user can learn about the exercise condition of the motion of the user.

In an exemplary embodiment of the present disclosure, the video playing apparatus may further include a play position determining unit to determine a play position of the video selected by the user to start playing the video from the play position before the motion of the user is acquired in real time by the motion acquiring unit 100. Here, the user can select a play position of the video in various existing manners. As one example, a user may select a play location of a video by taking an action of a location in the video that is desired to be played. That is, the play position determining unit is configured to determine the play position of the video selected by the user based on the play position selecting action of the user.

Specifically, the play position determination unit is configured to: and acquiring a play position selection action of the user. Here, the user may take any one of the actions in the video or the continuous action in any one of the video segments as the play position selection action. The method of obtaining the play position selection action of the user is as described above. For example, a user may be photographed with a multi-azimuth camera and a play position selection action of the user may be obtained in conjunction with a motion capture algorithm. As one example, the play position selection action of the user includes more than one continuous action. When the play position selection action of the user is acquired, first, one action of the user is acquired as the play position selection action. Then, when there is a video segment in the video that uniquely matches the play position selection action, the play position determination unit determines an n+1th action after the video segment in the video that uniquely matches the play position selection action as the play position. Here, n is a position adjustment amount, and n is a natural number greater than or equal to 1. That is, when there is a video segment in the video that uniquely matches the play position selection action, the play position is determined based on the position of the video segment and the position adjustment amount. For example, assuming that the play position selection action is uniquely matched with a video segment in a video, such as an mth video unit, and the current position adjustment amount is n, the determined play position is the mth+n+1th video unit.

In addition, the play position determining unit is further configured to, in response to the presence of a plurality of video segments in the video that match the current (including one action) play position selection action, cause the user to continue matching by increasing the number of actions in the current play position selection action. I.e. the user is prompted to further act to make a unique match. Here, the user may be prompted to further act by voice or a screen. The play position selection operation is gradually increased one by one after one operation is determined to be a non-unique match. Then, when the play position selection action of the user is further acquired, the play position selection action at this time comprises two continuous actions, and when a video segment uniquely matched with the current play position selection action exists in the video, the n+1th action after the video segment uniquely matched with the current play position selection action in the video is determined to be the play position. For example, assuming that the current play position selection action (including two consecutive actions) uniquely matches actions in the video, such as the mth video unit and the (m+1) th video unit, the determined play position is the (m+1+n+1) th video unit.

On the other hand, when the total matching time reaches the second predetermined time, determining an n+1th action after a video segment having the highest total matching degree among a plurality of video segments matched with the current play position selection action in the video as the play position, or determining an n+1th action after a first video segment among a plurality of video segments matched with the current play position selection action in the video as the play position. Here, the total matching time is a time from the first matching to the current matching. The second predetermined time may be arbitrarily set, for example, may be set to 10s or the like. That is, when the total matching time reaches the second predetermined time, the play position is determined based on the position and the position adjustment amount of the video segment having the highest total matching degree among the plurality of video segments, or based on the position and the position adjustment amount of the first video segment among the plurality of video segments. For example, assuming that the current play position selection action (including two actions) matches actions in video such as the mth and m+1th video units, the mth+8th and m+9th video units, the matching degree with the mth and m+1th video units is 78% and 78%, respectively, and the matching degree with the mth+8th and m+9th video units is 85% and 74%, respectively, when the total matching time reaches the second predetermined time, that is, when the total matching time is over, the determined play position is the (n+1) th action after the video segment having the highest total matching degree, that is, the (m+9+n+1) th video unit, or is the (n+1) th action after the first video segment of the two video segments, that is, the (m+1+n+1) th video unit.

That is, when the total matching time does not reach the second predetermined time, in response to the presence of a plurality of video segments in the video that match the current play position selection action, the user is caused to increase the number of actions in the current play position selection action, and when the total matching time reaches the second predetermined time, the n+1th action after the video segment in the video that has the highest total matching degree in the plurality of video segments that match the current play position selection action is determined as the play position, or the n+1th action after the first video segment in the plurality of video segments that match the current play position selection action is determined as the play position.

After the play position determining unit determines the play position of the video, the user may be notified by a prompt tone or a prompt screen, and then the action acquiring unit 100 starts acquiring the action of the user in real time. Since the user follows the video to exercise the sport motion, the motion performed by the user after the play position selection motion is a subsequent motion of the motion matching the play position selection motion in the video. For example, when it is determined that the play position of the video is the m+1+n+1-th video unit (i.e., the m+2+n-th video unit), the action (recognition unit) of the user acquired in real time corresponds to the m+2-th video unit in the video, that is, the action performed by the user after the play position selection action (the m-th video unit and the m+1-th video unit) is the action corresponding to the m+2-th video unit in the video.

As one example, the play position determining unit is configured to determine a play position of the video selected by the user in response to an initial action of the user. Here, the initial motion is a motion indicating that the user starts to perform motion exercise, and may be a static motion or a dynamic motion. As an example, the initiating action may be obtained as an identification unit. In addition, the initiation action may be a user-defined action or an action intercepted from the video, but the disclosure is not limited thereto. For example, in the scenario where the user exercises fancy basketball, the user holding action may be taken as the initiating action.

As one example, the play position determination unit is configured to prompt the user to select a play position of a video in response to an initial action of the user, and determine the play position of the video selected by the user. Here, the user may be prompted to select a play position of the video by voice or a screen.

As one example, the video playback device of the exemplary embodiment of the present disclosure may further include a playback end unit. The play ending unit ends the play of the video in response to the ending action of the user. Here, the ending motion is a motion indicating that the user ends the motion exercise, and may be a static motion or a dynamic motion. As an example, the ending action may be obtained as one recognition unit. In addition, the ending action may be a user-defined action or an action intercepted from the video, but the disclosure is not limited thereto. For example, in a case where the user exercises fancy basketball, the user holding action may be set as the ending action.

Further, it should be understood that various units in a video playback device according to an exemplary embodiment of the present disclosure may be implemented as hardware components and/or software components. The individual units may be implemented, for example, using a Field Programmable Gate Array (FPGA) or an Application Specific Integrated Circuit (ASIC), depending on the processing performed by the individual units as defined.

A computer-readable storage medium according to an exemplary embodiment of the present disclosure stores a computer program that, when executed by a processor, causes the processor to perform the video playback method of the above-described exemplary embodiment. The computer readable storage medium is any data storage device that can store data which can be read by a computer system. Examples of the computer readable storage medium include: read-only memory, random access memory, compact disc read-only, magnetic tape, floppy disk, optical data storage device, and carrier waves (such as data transmission through the internet via wired or wireless transmission paths).

A computing device according to an exemplary embodiment of the present disclosure includes: a processor and a memory. The memory has stored thereon a computer program which, when executed by a processor, implements the video playback method of the above-described exemplary embodiments.

Although a few exemplary embodiments of the present disclosure have been shown and described, it would be appreciated by those skilled in the art that changes may be made in these embodiments without departing from the principles and spirit of the disclosure, the scope of which is defined in the claims and their equivalents.

Claims

1. A video playing method, characterized in that the video playing method comprises:

acquiring actions of a user in real time;

when the action of the user is acquired, calculating the matching degree of the action of the user and the action corresponding to the action of the user in the video; and

when the matching degree is greater than a predetermined value, the play position of the video is adjusted based on one or more of the action speed of the user, the action accuracy of the user, and the change rate of the action in the video,

the step of adjusting the play position of the video based on one or more of the motion speed of the user, the motion accuracy of the user, and the rate of change of motion in the video comprises:

adjusting a position adjustment amount based on one or more of a motion speed of the user, a motion accuracy of the user, and a rate of change of motion in the video; and

A play position of the video is obtained based on a position of an action corresponding to the action of the user in the video and the position adjustment amount,

the position adjustment amount is a variable for dynamically adjusting the play position of the video.

2. The video playback method as recited in claim 1, wherein the video playback method further comprises:

and when the matching degree is smaller than or equal to a preset value, not adjusting the playing position of the video, and stopping playing the video when a preset condition is met.

3. The video playback method as recited in claim 2, wherein the predetermined condition comprises: the number of times that the degree of matching is continuously less than or equal to a predetermined value reaches a predetermined number of times, and the state that the degree of matching is less than or equal to the predetermined value continues for a first predetermined time.

4. The video playback method as recited in claim 1, wherein the video playback method further comprises:

and when the action of the user cannot be acquired, suspending playing the video.

5. The video playback method as recited in claim 1, wherein the video playback method further comprises:

and determining the playing position of the video selected by the user and starting to play the video from the playing position.

6. The video playback method as recited in claim 5, wherein the step of determining a playback position of the video selected by the user comprises:

a play position of the user-selected video is determined based on the play position selection action of the user.

7. The video playback method as recited in claim 6, wherein the step of determining the playback position of the video selected by the user based on the playback position selection action of the user comprises:

acquiring a play position selection action of the user; and

when a video segment uniquely matching the play position selection action exists in the video, determining an n+1th action after the video segment uniquely matching the play position selection action in the video as the play position, wherein n is a position adjustment amount and is a natural number greater than or equal to 1,

wherein the play position selection action comprises more than one continuous action.

8. The video playback method as recited in claim 7, wherein the step of determining the playback position of the video selected by the user based on the playback position selection action of the user further comprises:

and in response to the fact that a plurality of video segments matched with the current play position selection action exist in the video, enabling the user to increase the number of actions in the current play position selection action to continue matching, and determining an n+1th action after a video segment with highest total matching degree in the plurality of video segments matched with the current play position selection action in the video as the play position when the total matching time reaches a second preset time, or determining an n+1th action after a first video segment in the plurality of video segments matched with the current play position selection action in the video as the play position.

9. The video playback method as set forth in claim 5, wherein,

responsive to the user's initiating action, the step of determining the play position of the user-selected video is performed.

10. The video playback method as claimed in claim 6, wherein,

in response to the user's initiating action, prompting the user to select a play position of the video, and performing the step of determining the play position of the user-selected video.

11. The video playback method as recited in claim 1, wherein the video playback method further comprises:

and responding to the ending action of the user, and ending the playing of the video.

12. The video playing method according to claim 1, wherein the step of adjusting the playing position of the video comprises:

when the matching degree is larger than a preset value, judging whether more than one action with the change rate of 0 between actions corresponding to the actions of the user exist continuously after the actions corresponding to the actions of the user in the video; and

and determining whether to adjust the playing position of the video based on the judging result.

13. The video playback method as recited in claim 12, wherein the step of determining whether to adjust the playback position of the video based on the determination result comprises:

Determining not to adjust the playing position of the video when the judging result indicates that more than one action with the change rate of the actions corresponding to the actions of the user is 0 continuously exists, and suspending playing the video when the video is played to the action with the change rate of the actions corresponding to the actions of the user not being 0; and

when the judgment result indicates that more than one action with the change rate of the actions corresponding to the actions of the user is 0 is discontinuous, determining to adjust the playing position of the video based on more than one of the action speed of the user, the action accuracy of the user and the change rate of the actions in the video.

14. The video playback method as claimed in claim 1, wherein,

when the position adjustment amount is adjusted based on the operation speed of the user, the position adjustment amount is decreased if the operation speed is slow, and the position adjustment amount is increased if the operation speed is fast.

15. The video playback method as claimed in claim 1, wherein,

when the position adjustment amount is adjusted based on the motion accuracy of the user, the position adjustment amount is increased if the motion accuracy is increased, and the position adjustment amount is decreased if the motion accuracy is decreased.

16. The video playback method as claimed in claim 1, wherein,

when the position adjustment amount is adjusted based on the rate of change of the motion in the video, the position adjustment amount is decreased if the rate of change is increased, and the position adjustment amount is increased if the rate of change is decreased.

17. The video playback method as claimed in claim 1, wherein,

the position adjustment amount is adjusted by weighting when the position adjustment amount is adjusted based on two or more of the user's motion speed, the user's motion accuracy, and the rate of change of motion in the video.

18. The video playback method as claimed in claim 1, wherein,

the actions of the user are obtained as recognition units, one recognition unit representing an action, the recognition unit comprising a plurality of frames and comprising at least one key frame.

19. The method for video playback as set forth in claim 18, wherein,

the action corresponding to the action of the user in the video is represented as a video unit, the video unit is obtained by dividing the video according to the action, and the video unit comprises a plurality of frames and at least one key frame.

20. A video playback device, the video playback device comprising:

an action acquisition unit configured to acquire an action of a user in real time;

a matching degree calculating unit configured to calculate, when an action of the user is acquired, a matching degree of the action of the user and an action corresponding to the action of the user in the video; and

a play position adjustment unit configured to adjust a play position of the video based on one or more of a motion speed of the user, a motion accuracy of the user, and a rate of change of motion in the video when the matching degree is greater than a predetermined value,

the play position adjustment unit is configured to:

21. The video playback device according to claim 20, wherein the playback position adjustment unit is configured not to adjust the playback position of the video when the degree of matching is less than or equal to a predetermined value, and to pause playback of the video when a predetermined condition is satisfied.

22. The video playback device of claim 21, wherein the predetermined condition comprises: the number of times that the degree of matching is continuously less than or equal to a predetermined value reaches a predetermined number of times, and the state that the degree of matching is less than or equal to the predetermined value continues for a first predetermined time.

23. The video playback device of claim 20, wherein the video playback device further comprises: and a pause playing unit configured to pause playing of the video when the action acquisition unit cannot acquire the action of the user.

24. The video playback device of claim 20, wherein the video playback device further comprises:

a play position determining unit configured to determine a play position of the video selected by the user to start playing the video from the play position.

25. The video playback device of claim 24, wherein the playback position determination unit is configured to determine a playback position of the video selected by the user based on a playback position selection action of the user.

26. The video playback device of claim 25, wherein the playback position determination unit is configured to:

Acquiring a play position selection action of the user; and

27. The video playback device of claim 26, wherein the playback position determination unit is further configured to:

28. The video playback device of claim 24, wherein the playback position determination unit is configured to determine the playback position of the video selected by the user in response to an initial action by the user.

29. The video playback device of claim 25, wherein the playback position determination unit is configured to prompt the user to select a playback position of a video in response to an initial action of the user, and to determine the playback position of the video selected by the user.

30. The video playback device of claim 20, wherein the video playback device further comprises:

and the playing ending unit responds to the ending action of the user and ends the playing of the video.

31. The video playback device of claim 20, wherein the playback position adjustment unit is configured to:

32. The video playback device of claim 31, wherein the playback position adjustment unit is further configured to:

33. The video playback device of claim 20, wherein,

the play position adjustment unit is configured to, when adjusting the position adjustment amount based on the action speed of the user, decrease the position adjustment amount if the action speed is slow, and increase the position adjustment amount if the action speed is fast.

34. The video playback device of claim 20, wherein,

the play position adjustment unit is configured to, when adjusting the position adjustment amount based on the action accuracy of the user, increase the position adjustment amount if the action accuracy increases, and decrease the position adjustment amount if the action accuracy decreases.

35. The video playback device of claim 20, wherein,

the play position adjustment unit is configured to, when adjusting the position adjustment amount based on a rate of change of an action in the video, decrease the position adjustment amount if the rate of change increases, and increase the position adjustment amount if the rate of change decreases.

36. The video playback device of claim 20, wherein,

the play position adjustment unit is configured to adjust the position adjustment amount by weighting when the position adjustment amount is adjusted based on two or more of a speed of motion of the user, an accuracy of motion of the user, and a rate of change of motion in the video.

37. The video playback device of claim 20, wherein,

38. The video playback device of claim 37, wherein,

the actions corresponding to the actions of the user in the video are video units, the video units are obtained by dividing the video according to the actions, and the video units comprise a plurality of frames and at least one key frame.

39. A computer readable storage medium storing a computer program, characterized in that the video playing method of any one of claims 1 to 19 is implemented when the computer program is executed by a processor.

40. A computing device, the computing device comprising:

a processor;

a memory storing a computer program which, when executed by the processor, implements the video playback method of any one of claims 1 to 19.