Action display method, device and electronic equipment
By predicting the movement trajectory and movement of skiers and displaying predicted movements and target movements, the problem of poor viewing experience of the audience in the live broadcast of ski competitions is solved, and the effect of competition and training is improved.
Patent Information
- Application Number
- CN202210713089.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-06-22
- Publication Date
- 2024-12-17
- Estimated Expiration
- 2042-06-22
AI Technical Summary
In the live broadcast of ski competitions, the audience's viewing experience is poor, and it is difficult to understand the players' movement completion status and skills in real time.
By obtaining the movement parameter information of the target person, predicting their movement trajectory and movement, and comparing them with the pre-acquisitioned target movement trajectory, displaying the predicted movement and target movement, improving the audience's real-time understanding and experience.
It improves the audience's real-time understanding and viewing experience of the contestants' movements, helps the contestants to standardize the movements during training, and improves the effect of competitions and training.
Smart Images
Figure CN115083017B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of video technology, and in particular to an action display method, device and electronic equipment. Background Art
[0002] In live broadcasts of skiing competitions, the real-time performance of the athletes is usually broadcast live to the audience, and the completion of the athletes' aerial skills and movements is restored through video playback, as well as the commentator's comments on the competition results to obtain the athletes' performance, resulting in a poor viewing experience. Summary of the invention
[0003] The present application provides an action display method, device and electronic device to solve the problem of poor viewing experience.
[0004] In a first aspect, an embodiment of the present application provides an action display method, including:
[0005] Obtain the motion parameter information of the target person;
[0006] Based on the motion parameter information, predicting the motion trajectory of the target person to obtain a predicted motion trajectory;
[0007] Based on the predicted motion trajectory and the pre-acquired target motion trajectory, acquiring a predicted action of the target person at a target time, and a target action corresponding to the predicted action;
[0008] The predicted action and the target action are displayed.
[0009] In a second aspect, the embodiment of the present application further provides an action display device, including:
[0010] The first acquisition module is used to acquire the motion parameter information of the target person;
[0011] A prediction module, used to predict the motion trajectory of the target person based on the motion parameter information to obtain a predicted motion trajectory;
[0012] A second acquisition module, configured to acquire a predicted action of the target person at a target time and a target action corresponding to the predicted action based on the predicted motion trajectory and the pre-acquired target motion trajectory;
[0013] The first display module is used to display the predicted action and the target action.
[0014] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a transceiver, a memory, a processor, and a program stored in the memory and executable on the processor; the processor is used to read the program in the memory to implement the steps in the method described in the first aspect of the embodiment of the present application.
[0015] In a fourth aspect, an embodiment of the present application further provides a readable storage medium, on which a program is stored, and when the program is executed by a processor, the steps in the method described in the first aspect of the embodiment of the present application are implemented.
[0016] In the embodiment of the present application, the motion parameter information of the target person is obtained; based on the motion parameter information, the motion trajectory of the target person is predicted to obtain a predicted motion trajectory; based on the predicted motion trajectory and the pre-acquired target motion trajectory, the predicted action of the target person at the target time and the target action corresponding to the predicted action are obtained; the predicted action and the target action are displayed. That is, during the movement of the target person, the predicted action of the target person at the target time and the target action corresponding to the predicted action can be displayed, and the audience can know the completion status of the action of the target person by comparing the predicted action with the target action, thereby improving the viewing experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to more clearly illustrate the technical solution of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0018] Figure 1 It is a flowchart of an action display method provided in an embodiment of the present application;
[0019] Figure 2 is a schematic diagram of multiple points in a predicted trajectory curve provided in an embodiment of the present application;
[0020] Figure 3 is a schematic diagram of a display of a predicted action provided in an embodiment of the present application;
[0021] Figure 4 It is a structural schematic diagram of an action display device provided in an embodiment of the present application;
[0022] Figure 5 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0023] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0024] The terms "first", "second" etc. in the embodiments of the present application are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. In addition, the terms "include" and "have" and any variation thereof are intended to cover non-exclusive inclusions, for example, the process, method, system, product or equipment comprising a series of steps or units need not be limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment. In addition, "and / or" is used in the present application to represent at least one of connected objects, such as A and / or B and / or C, representing the inclusion of separate A, separate B, separate C, and A and B all exist, B and C all exist, A and C all exist, and 7 situations that A, B and C all exist.
[0025] See also Figure 1 , Figure 1 is a flowchart of an action display method provided in an embodiment of the present application, such as Figure 1 As shown, the following steps are included:
[0026] Step 101: Obtain motion parameter information of a target person.
[0027] The target person may be any player in a competition or any athlete in the process of training for a sport, for example, a player participating in a skiing competition or an athlete in the process of training for a skiing event.
[0028] The above-mentioned motion parameter information may include parameters that affect the motion trajectory of the above-mentioned target person. For example, in skiing, the wind force and direction of the ski resort, the speed of the athlete, the force area of the athlete, etc. all have an impact on his motion trajectory.
[0029] Optionally, the motion parameter information includes at least one of the following:
[0030] Wind power;
[0031] wind direction;
[0032] The speed and direction of the target person when leaving the first location;
[0033] The force-bearing area of the target person.
[0034] In skiing events, such as big air, halfpipe, and obstacle course, the athlete's motion trajectory can be predicted based on the above motion parameter information.
[0035] Step 102: predict the motion trajectory of the target person based on the motion parameter information to obtain a predicted motion trajectory.
[0036] It should be noted that the above-mentioned motion trajectory will be affected by the above-mentioned motion parameter information. For example, the speed of a player in the same competition with the wind will be greater than the speed against the wind, and the angle between the wind direction and the player will also change the degree of influence of the wind on the player.
[0037] Specifically, the relationship between the above-mentioned motion parameter information and the motion trajectory can be determined by curve fitting. For example, the motion parameter information and the motion trajectory of the player can be curve fitted through a large amount of historical data to determine the functional relationship between the above-mentioned motion parameter information and the above-mentioned predicted motion trajectory, and the motion trajectory of the above-mentioned target person can be predicted using the functional relationship; or, it can be determined by a neural network model. During the training process, the historical motion parameter information is used as the input of the neural network model, and the corresponding historical motion trajectory is used as the output of the neural network model. The above-mentioned neural network model is iteratively updated through a large amount of historical data, and the updated neural network model is used to predict the motion trajectory of the above-mentioned target person.
[0038] Step 103: Based on the predicted motion trajectory and the pre-acquired target motion trajectory, the predicted action of the target person at the target time and the target action corresponding to the predicted action are acquired.
[0039] The predicted action may be an action that is predicted to have a possible error, or an action that may be completed in a standard manner (ie, a wonderful moment of the action), or may be an action that is predicted after a preset period of time.
[0040] Specifically, the above-mentioned target time can be a predetermined time or time interval, so that the above-mentioned predicted action displayed is the predicted action for a period of time after the set time or the current time; the above-mentioned target time can also be determined based on the above-mentioned predicted motion trajectory and the above-mentioned target motion trajectory, that is, firstly, through the above-mentioned predicted motion trajectory determination and the above-mentioned target motion trajectory, the target time when the above-mentioned target person may make an erroneous action, or the target time when the corresponding action may be completed in a standardized manner is obtained, and then the predicted action of the above-mentioned target time is obtained according to the above-mentioned predicted motion trajectory, and the target action of the above-mentioned target time is obtained according to the above-mentioned target motion trajectory.
[0041] Step 104: Display the predicted action and the target action.
[0042] Among them, the display of the above-mentioned predicted action and the above-mentioned target action can be carried out in a variety of ways. For example, during the process of live video broadcast of the movement process of the above-mentioned target person, the above-mentioned predicted action and the above-mentioned target action can be displayed in a small window while the actual movement process of the above-mentioned target person is broadcast live. Thus, the action of the above-mentioned target person at the above-mentioned target time can be predicted, and the audience can be informed of the above-mentioned target action corresponding to the above-mentioned predicted action, so that the next movement trajectory and action of the above-mentioned target person can be predicted in advance and informed to the audience.
[0043] In the embodiment of the present application, the motion parameter information of the target person is obtained; based on the motion parameter information, the motion trajectory of the target person is predicted to obtain a predicted motion trajectory; based on the predicted motion trajectory and the pre-acquired target motion trajectory, the predicted action of the target person at the target time and the target action corresponding to the predicted action are obtained; the predicted action and the target action are displayed. That is, during the movement of the target person, the predicted action of the target person at the target time and the target action corresponding to the predicted action can be displayed, and the audience can know the completion status of the action of the target person by comparing the predicted action with the target action, thereby improving the viewing experience.
[0044] In addition, the action prediction display method provided in the embodiment of the present application can help players standardize their actions during training by displaying predicted actions and target actions, thereby helping to improve the training effect of the players.
[0045] Optionally, the motion parameter information includes motion parameter information of the target person in a skiing scene.
[0046] In the skiing scene, the target person’s trajectory in the next period of time can be predicted by obtaining the target person’s motion parameter information at a certain position. For example, in the ski jumping project, the target person’s skiing trajectory after leaving the upper slope can be predicted by obtaining the target person’s motion parameter information after leaving the upper slope.
[0047] It should be noted that the above skiing scene can be a live broadcast of a competition or a training scene of ski athletes.
[0048] During the live broadcast of a skiing competition, the player's motion parameter information can be obtained to make a real-time prediction of the player's motion trajectory, and compared with the corresponding target motion trajectory, so as to predict the moment when the player gets a full score or makes an error, and display the player's predicted action and target action at that moment. In this way, the audience can understand the standard actions in the skiing process in advance through the displayed predicted actions and target actions, and can judge the standardization of the actions actually displayed by the player at that moment, thereby enhancing the audience's experience of watching the skiing competition.
[0049] During skiing training, similar to the above-mentioned live skiing competition prediction process, the predicted motion trajectory, the corresponding target motion trajectory and the trajectory actually completed by the athlete can be used to guide the athlete's training process, help them standardize their movements, and help improve the athlete's training effect.
[0050] Optionally, in step 102, based on the motion parameter information, the motion trajectory of the target person is predicted to obtain the predicted motion trajectory, including:
[0051] The motion parameter information is input into the motion trajectory prediction model to obtain the predicted motion trajectory of the target person;
[0052] Among them, the motion trajectory prediction model is trained using historical motion parameter information and historical motion trajectories.
[0053] Among them, the above-mentioned motion trajectory prediction model can be determined by curve fitting, or by using a neural network model. For example, for the curve fitting method, one or more curve models can be selected first, and the selected curve model and curve model parameters can be determined by fitting multiple historical data; for example, the neural network model can be iteratively trained using multiple historical data to determine the model parameters of the neural network model.
[0054] When the motion trajectory prediction model is determined by using curve fitting, it can be obtained based on the historical motion parameter information and the historical motion trajectory fitting, for example, by the least squares method, by using analytical expressions to approximate discrete data, and the like.
[0055] Optionally, the motion trajectory prediction model includes multiple sub-prediction models, the motion parameter information includes motion parameter information of multiple points of the target person, and different sub-prediction models are used to predict the trajectories of different points of the target person;
[0056] The motion parameter information is input into the motion trajectory prediction model to obtain the predicted motion trajectory of the target person, including:
[0057] Inputting motion parameter information of each point in the multiple points into the corresponding sub-prediction model to obtain a predicted trajectory of each point;
[0058] Based on the predicted trajectories of multiple points, the predicted movement trajectory of the target person is determined.
[0059] Specifically, for the motion trajectory of the above-mentioned target person, a prediction motion trajectory model can be constructed according to different points. The above-mentioned multiple points can be determined according to application scenarios or experience values. For example, for a skiing competition, the player's head, arms, waist, knees, ankles and the front edge of the skis used by the player all affect the final judging score. Then, in the skiing competition, the player's head, arms, waist, knees, ankles and the front edge of the skis used by the player can be used as different points, and sub-prediction models can be constructed respectively to realize the motion trajectory prediction of each point.
[0060] Moreover, after obtaining the predicted trajectories of the above-mentioned multiple points based on the above-mentioned multiple sub-prediction models, the overall predicted motion trajectory of the above-mentioned target person can be obtained. For example, a virtual character can be pre-constructed, and according to the above-mentioned multiple points, the virtual character can be made to move according to the predicted trajectory of the above-mentioned multiple points, and the predicted action corresponding to the virtual character can be obtained at the above-mentioned target time, thereby improving the viewing experience of the above-mentioned predicted action display.
[0061] In addition, the display of the above-mentioned target action can also refer to the display method of the above-mentioned predicted action, so that by comparing the above-mentioned predicted action with the above-mentioned target action, the audience can obtain in advance whether a certain action of the player during the game is standardized, complete, and the degree of completion of the action, thereby improving the audience's real-time viewing experience during the live broadcast of the game.
[0062] Optionally, the predicted action trajectory includes M first segmented trajectories, where M is a positive integer;
[0063] After predicting the motion trajectory of the target person based on the motion parameter information to obtain the predicted motion trajectory, the method further includes:
[0064] Obtaining M second segmented trajectories corresponding to the M first segmented trajectories in the target motion trajectory;
[0065] Matching each first segmented trajectory in the M first segmented trajectories with the corresponding second segmented trajectory, and determining a prediction score of each first segmented trajectory, where the prediction score is used to indicate a matching degree between the first segmented trajectory and the corresponding second segmented trajectory;
[0066] Based on the predicted scores of the M first segmented trajectories, the score of the target person is obtained, and the score of the target person is used to indicate the matching degree between the predicted motion trajectory and the target motion trajectory.
[0067] Among them, the above-mentioned M first segmented trajectories can be obtained by dividing the above-mentioned predicted action trajectory according to preset time intervals, and correspondingly, the above-mentioned M second segmented trajectories can also be obtained by dividing the above-mentioned target action trajectory according to preset time intervals, that is, each of the above-mentioned first segmented trajectory corresponds to a second segmented trajectory at the same time interval.
[0068] Among them, the above-mentioned M first segmented trajectories are matched with the corresponding second segmented trajectories to determine the matching degree of the two trajectories. For example, multiple points can be taken in the above-mentioned first segmented trajectory, and multiple corresponding points can be taken in the above-mentioned second segmented trajectory. The matching degree between the two trajectories is determined based on the distance between these multiple points. The larger the distance, the smaller the matching degree. The predicted scores of the above-mentioned M first segmented trajectories are determined based on the matching degree. Among them, the predicted score of the trajectory with a high matching degree with the corresponding second segmented trajectory is higher than the predicted score of the trajectory with a low matching degree with the corresponding second segmented trajectory. In addition, the score of the above-mentioned target person can be determined according to the weight corresponding to each first segmented trajectory.
[0069] Specifically, the above-mentioned prediction score can be obtained directly or indirectly based on the result of matching each of the above-mentioned first segmented trajectories with the corresponding second segmented trajectories. For example, the matching degree between the above-mentioned first segmented trajectory and the corresponding second segmented trajectory can be calculated, and the above-mentioned matching degree can be directly used as the prediction score of the above-mentioned first segmented trajectory; or the prediction score of the above-mentioned first segmented trajectory can be determined based on the above-mentioned matching degree division intervals. For example, the matching degree of complete match is set to 1, and the matching degree of complete mismatch is set to 0. According to the matching degree from 0 to 1, it can be divided into multiple intervals. When the matching degree between the above-mentioned first segmented trajectory and the corresponding second segmented trajectory is in the first interval, the prediction score of the first segmented trajectory can be determined as the first prediction score. When the matching degree between the above-mentioned first segmented trajectory and the corresponding second segmented trajectory is in the second interval, the prediction score of the first segmented trajectory is determined as the second prediction score, and so on. The specific interval division and the corresponding prediction score can be determined according to actual conditions.
[0070] It should be noted that the M-segment trajectory may correspond to the entire trajectory or a portion of the predicted action trajectory. For example, when predicting the predicted action of the target person in real time, the M-segment trajectory may correspond to the entire trajectory of the predicted action trajectory, thereby predicting whether the target person can complete each subsequent action in a standardized manner. Alternatively, when predicting the final score of the target person, for example, in a ski jumping competition, if the final score of the player is related to the distance from the landing point, then a portion of the predicted action trajectory may be selected as the M-segment trajectory, thereby predicting the final score of the player according to the M-segment trajectory.
[0071] In this implementation, by matching each of the M first segmented trajectories with the corresponding second segmented trajectories, the predicted scores of the M first segmented trajectories are determined, and the predicted scores are used to indicate the degree of matching between each first segmented trajectory and the corresponding second segmented trajectory; based on the predicted scores of the M first segmented trajectories, the score of the target person is obtained, and the score of the target person is used to indicate the degree of matching between the predicted motion trajectory and the target motion trajectory. That is, the present application divides the predicted motion trajectory into the M first segmented trajectories, and determines the predicted scores of the M first segmented trajectories respectively, thereby obtaining the score of the target person and improving the prediction accuracy of the score of the target person.
[0072] In addition, in this embodiment, the score of the target person is obtained based on the predicted scores of the M first segmented trajectories, which can also be used as a reference for the referee's scoring, thereby improving the objectivity of the scoring.
[0073] Optionally, in step 103, based on the predicted motion trajectory and the pre-acquired target motion trajectory, the predicted action of the target person at the target time and the target action corresponding to the predicted action are acquired, including:
[0074] For each first segmented trajectory of the M first segmented trajectories, obtaining a first deviation between the first segmented trajectory and the corresponding second segmented trajectory;
[0075] The time of the target segmented trajectory among the M first segmented trajectories is taken as the target time, the target segmented trajectory is the segmented trajectory corresponding to the target deviation, and the target deviation is the deviation that satisfies the first preset condition among the M first deviations;
[0076] Based on the predicted motion trajectory, obtain the predicted action of the target person at the target time;
[0077] Based on the target motion trajectory, the target action corresponding to the predicted action is obtained.
[0078] Among them, the above-mentioned first deviation degree can represent the degree of deviation between the above-mentioned first segmented trajectory and the corresponding second segmented trajectory. The above-mentioned first deviation degree can be determined by calculating the distance between the above-mentioned multiple points with reference to the method for determining the matching degree between the above-mentioned first segmented trajectory and the corresponding second segmented trajectory. The larger the distance, the larger the first deviation degree.
[0079] Among them, the above-mentioned target time can be the time when an erroneous action is predicted to occur (the first deviation is large), or it can be the time when a standard action is predicted to occur (the first deviation is small), and the above-mentioned target time can include the time of at least one first segmented trajectory.
[0080] Specifically, based on the predicted motion trajectory, the predicted action of the target person at the target time is obtained, including:
[0081] Obtain the position of the target person at the target time in the predicted trajectory of each of the multiple points;
[0082] Based on the position of the target person at the target time in the predicted trajectory of each of the multiple points, a predicted action of the target person is determined.
[0083] Among them, each point corresponds to a predicted trajectory. For example, taking the head of the target person as a point, a motion trajectory will be formed during the movement of the head point. In the predicted trajectory corresponding to the head point, the head point corresponds to a position point at each moment, that is, in the predicted trajectory, after determining the target time, the position of the target person's head can be confirmed.
[0084] Correspondingly, by obtaining the predicted trajectory of each point of the target person and determining the position of each point of the target person at the target time, the predicted action of the target person at the target time can be determined. Specifically, taking the above-mentioned multiple points including head points, arm points, waist points, knee points and ankle points as an example, by determining the head position, arm position, waist position, knee position and ankle position of the target person at the target time, combining the above positions with the human body shape, the action at the target time can be determined. When displaying the above-mentioned predicted action, the target person can be modeled in advance, and the action of the modeled target person can be generated based on the above-mentioned determined positions, so as to display the above-mentioned predicted action. Among them, the display of the above-mentioned target action can also parameterize the display method of the above-mentioned predicted action, which will not be repeated here.
[0085] Optionally, the first preset condition includes any one of the following:
[0086] The first deviation is less than or equal to a first threshold;
[0087] The first deviation is greater than a second threshold;
[0088] The first threshold is smaller than the second threshold.
[0089] The first threshold and the second threshold may be predetermined, for example, according to empirical values or competition rules.
[0090] When the above-mentioned first deviation is less than or equal to the above-mentioned first threshold, it can be considered that the predicted action of the above-mentioned target person and the corresponding target action have a small deviation, and it can be predicted that the above-mentioned target person will perform standard actions at the corresponding time. In this way, by displaying the predicted action and the target action at that time, it is possible to predict in advance and inform the audience that the wonderful moments are about to appear. When the wonderful moments actually occur, the audience can compare the above-mentioned predicted action with the above-mentioned target action to know whether the corresponding actions performed by the above-mentioned target person are standardized, complete, and the completion status, thereby improving the audience's viewing experience.
[0091] When the above-mentioned first deviation is greater than the above-mentioned second threshold value, it can be considered that the predicted action of the above-mentioned target person deviates greatly from the corresponding target action, and it can be predicted that the above-mentioned target person will make a wrong action at the corresponding time. In this way, by showing the predicted action and the target action at that time, the audience can be predicted and informed in advance that the wrong action is about to occur. By comparing the above-mentioned predicted action with the above-mentioned target action, the audience can know why the above-mentioned target person's action is wrong, which can improve the audience's real-time viewing experience.
[0092] Optionally, the target motion trajectory includes multiple target trajectories, and different target trajectories correspond to different points;
[0093] After inputting the motion parameter information of each of the multiple points into the corresponding sub-prediction model to obtain the predicted trajectory of each point, the method further includes:
[0094] Obtaining a second deviation between a predicted trajectory of a target point and a corresponding target trajectory, where the target point is any one of the multiple points;
[0095] When the second deviation satisfies the second preset condition, the target point is displayed.
[0096] The calculation of the second deviation can refer to the calculation method of the first deviation.
[0097] Optionally, the second preset condition may include any one of the following:
[0098] The second deviation is less than or equal to the first threshold;
[0099] The second deviation is greater than the second threshold.
[0100] That is, if the second deviation between the predicted trajectory of the above-mentioned target point and the corresponding target trajectory is less than or equal to the first threshold, it can be considered that the predicted action at the position of the above-mentioned target point is relatively standard. By displaying the target point, the audience can be informed of the specific position of the above-mentioned target point, so that the audience can know the standard style of the predicted action and improve their understanding of the game.
[0101] If the second deviation between the predicted trajectory of the above-mentioned target point and the corresponding target trajectory is greater than the second threshold, it can be considered that the position where the predicted action is about to make an error is the above-mentioned target point. By displaying the above-mentioned target point, the audience can be informed of the specific position of the error, so that the audience can understand the specific position of the error in advance for the upcoming erroneous action.
[0102] It should be noted that the display of the above-mentioned target points can be displayed in a visually enhanced manner, for example, by marking arrows at the above-mentioned target points, by using different colors to mark the above-mentioned target points, by using specific marks at the above-mentioned target points, etc., so that the audience can see the above-mentioned target points.
[0103] For better understanding, the following are some examples:
[0104] This embodiment of the application takes the big jump in the skiing event as an example to illustrate a method for displaying an action, and the specific steps are as follows:
[0105] Step 1: Standardize action modeling;
[0106] For example, the standard processing actions of a specified action can be modeled and displayed throughout the entire process through 3D action digital intelligence modeling;
[0107] Step 2: Site modeling;
[0108] For example, the large platform slope is 40 meters high and 138 meters long. The upper half of the slope is used for the athletes to accelerate, and a curved platform is set in the middle for the athletes to take off and perform actions;
[0109] Step 3: Character modeling;
[0110] Set up a virtual character image to contrast with the real player's movements. According to the current rules of skiing, skiers are divided into several fixed positions, such as head, arms, waist, knees, ankles, and the front edge of the ski board. The following steps are explained in detail using the head position point trajectory as an example;
[0111] Step 4: Collect the factors that affect the motion trajectory of the contestants when they leave the arc diving platform, and predict the trajectory of the contestants in the air, which specifically includes the following process:
[0112] (1) Obtain the factors that affect the player's movement trajectory;
[0113] Factors that affect the athlete's trajectory include: wind force (observed at the ski resort), wind direction (angle between wind direction and athlete's horizontal movement, observed at the ski resort), direction of leaving the upper slope (angle between the athlete's sliding direction leaving the upper slope and the horizontal direction), initial speed of leaving the upper slope, and the force area formed by the athlete's curled body (observed when the athlete is skiing);
[0114] (2) Based on the factors that affect the athlete's motion trajectory, the trajectory (x, y) of the athlete leaving the arc diving platform is constructed as:
[0115]
[0116] Among them, h(F, θ, α, V, H, t) = e F sinθ+VH sinα (c1+c2t);
[0117] v(F, θ, α, V, H, t)=e F cosθ+VH cosα (c3+c4t);
[0118] Among them, F represents wind force, θ represents wind direction angle, α represents the direction of the player leaving the upper half of the slope, V represents the initial speed of the player leaving the upper half of the slope, H represents the force area of the player, c1, c2, c3 and c4 are model training constants, and t represents the time when the player leaves the upper half of the slope;
[0119] (3) Based on the above steps, a predicted trajectory curve of the player is formed;
[0120] Take multiple points in the predicted trajectory curve, such as Figure 2 As shown in the figure, X represents the distance of the athlete from the starting point after the jump, Y represents the height of the athlete in the air, and X is obtained by v(F, θ, α, V, H, t), and Y is obtained by h(F, θ, α, V, H, t);
[0121] Step 5: Determine the predicted score of the player based on the predicted trajectory curve obtained in step 4. The specific process is as follows:
[0122] (1) Construct a full-score action trajectory model through the point trajectories of the standard action constructed in step 1;
[0123] (2) Take n+1 sample data from the full-score motion trajectory model to obtain a sample set: A = {(x0, y0), (x1, y1), ..., (x n ,y n )};
[0124] Construct a trajectory fitting function:
[0125] in,
[0126] Among them, y j represents the Y-axis coordinate of the jth sample, r j represents the X-axis coordinate of the jth sample, x m Indicates the X-axis coordinate of the mth sample.
[0127] (3) The trajectory curve in step 4 is matched with the full score fitting function trajectory L(x) in real time to obtain the predicted score of the player in each segment in the air. The specific process is as follows:
[0128] According to the actual situation of the ski track, the maximum skiing distance is divided into M sections, and the score weight of each section is
[0129] Through model training, the standard trajectory reaching interval value R of each segment of M is obtainedi , i∈{1, 2, ..., M}, when the player's trajectory deviates from the distance d i ≤R i When , the proportion of the obtained score in the i-th segment area is determined to be ω i ;
[0130] From the above M segments, randomly select N predicted trajectory samples of the players in the kth segment: B = {(x1, y1), (x2, y2), ..., (x n ,y n )};
[0131] Then let the set C = {(x1, y1′), (x2, y2′), ..., (x n ,y n ′)},y j ′=L(x j ), j∈{1, 2, ..., M}, set C is a set of sample data obtained from n sample data obtained from the trajectory of the full-score player;
[0132] Construct the deviation function between the player's predicted trajectory and the full score action:
[0133] in,
[0134]
[0135]
[0136] Among them, d k Indicates the deviation between the player's predicted trajectory in the k-th area and the full score action.
[0137] Through the above calculation, if we get d k ≤R k ,k∈{1,2,......,M}, then the player’s trajectory score in the air can be predicted in real time: S1=∑ k∈{1,2,……,M} ω k ×C, where ω k represents the percentage of obtained scores in the kth segment, and C represents the full score;
[0138] The above is the score calculated for the head point in the sliding track. Similarly, the score of the arm point S2, the score of the waist point S3, the score of the knee point S4, the score of the ankle point S5 and the score of the front point of the snowboard S6 can be calculated. The final predicted score of the player is determined according to the scores of the above six points. Among them, S u represents the score of point u, v u Represents the score weight of point u;
[0139] Step 6: Display the real-time score and final score obtained in step 5 based on the venue model constructed in step 2 and the character model constructed in step 3. By comparing the difference between the predicted score of each link and the full score, it can be concluded that the contestants may perform well or poorly in this link and give hints.
[0140] Specifically, the predicted screen is generated through the data calculated above, and the full score action can be displayed under the current action of the player. If the player is predicted to make a mistake in 5 seconds based on the above prediction results, the predicted action of the player in 5 seconds and the full score action in 5 seconds can also be displayed, and the action points of the player can be marked to prompt the audience. Or, Figure 3 As shown, the comparison between the predicted action trajectory of the contestant and the corresponding full score action trajectory can also be displayed, and the possible erroneous actions of the contestant can be more intuitively displayed through the above comparison.
[0141] In the embodiment of the present application, by modeling the standard action, venue and character respectively; and by the trajectory of each point of the standard action in the standard action model, a full score action trajectory curve is constructed; taking the skiing project-women's big jump as an example, the factors affecting the athlete's motion trajectory (wind force, wind direction, direction of leaving the upper half of the slope, speed and the force area of the athlete, etc.) are collected, and the trajectory of the contestant leaving the arc jump is constructed based on the factors to form the athlete's predicted trajectory curve in the air; the predicted trajectory curve is matched with the full score action trajectory curve in step 2 in real time to obtain the predicted score of each section of the athlete in the air; by predicting the difference between the score of each section and the full score, the good or bad performance of the athlete in this link is obtained, and corresponding prompts are given. In this way, the predicted trajectory is constructed by the wind force, direction, speed, force area in the air, etc. when the player leaves the slide, and the predicted trajectory is matched and calculated with the full score curve, and the wonderful performance of the player in the key link and the link that may play a mistake are predicted in real time, and it is displayed through the video screen, which can reduce the audience's viewing threshold for professional skill projects and the audience's participation in live broadcast projects.
[0142] See also Figure 4 , Figure 4 4 is a schematic diagram of the structure of an action display device provided in an embodiment of the present application. As shown in FIG. 4 , the action display 400 includes:
[0143] The first acquisition module 401 is used to acquire motion parameter information of a target person;
[0144] A prediction module 402 is used to predict the motion trajectory of the target person based on the motion parameter information to obtain a predicted motion trajectory;
[0145] The second acquisition module 403 is used to acquire the predicted action of the target person at the target time and the target action corresponding to the predicted action based on the predicted motion trajectory and the pre-acquired target motion trajectory;
[0146] The first display module 404 is used to display the predicted action and the target action.
[0147] Optionally, the prediction module 402 includes:
[0148] A prediction unit, used to input motion parameter information into a motion trajectory prediction model to obtain a predicted motion trajectory of a target person;
[0149] Among them, the motion trajectory prediction model is trained using historical motion parameter information and historical motion trajectories.
[0150] Optionally, the motion trajectory prediction model includes multiple sub-prediction models, the motion parameter information includes motion parameter information of multiple points of the target person, and different sub-prediction models are used to predict the trajectories of different points of the target person;
[0151] Prediction unit, including:
[0152] A prediction subunit, used for inputting motion parameter information of each point in the plurality of points into a corresponding sub-prediction model to obtain a predicted trajectory of each point;
[0153] The determination subunit is used to determine the predicted motion trajectory of the target person based on the predicted trajectories of multiple points.
[0154] Optionally, the motion parameter information includes at least one of the following:
[0155] Wind power;
[0156] wind direction;
[0157] The speed and direction of the target person as he or she leaves the first location;
[0158] The force-bearing area of the target person.
[0159] Optionally, the predicted action trajectory includes M first segmented trajectories, where M is a positive integer;
[0160] Action Show 400 also includes:
[0161] A third acquisition module is used to acquire M second segmented trajectories corresponding to the M first segmented trajectories in the target motion trajectory;
[0162] A matching module, used to match each first segmented trajectory in the M first segmented trajectories with the corresponding second segmented trajectory, and determine a prediction score of each first segmented trajectory, where the prediction score is used to indicate a matching degree between the first segmented trajectory and the corresponding second segmented trajectory;
[0163] The fourth acquisition module is used to acquire the score of the target person based on the predicted scores of the M first segmented trajectories, where the score of the target person is used to indicate the matching degree between the predicted motion trajectory and the target motion trajectory.
[0164] Optionally, the second acquisition module 403 includes:
[0165] A first acquisition unit is used to acquire, for each first segmented trajectory of the M first segmented trajectories, a first deviation between the first segmented trajectory and the corresponding second segmented trajectory;
[0166] a determination unit, configured to use the time of a target segmented trajectory among the M first segmented trajectories as a target time, wherein the target segmented trajectory is a segmented trajectory corresponding to a target deviation, and the target deviation is a deviation among the M first deviations that satisfies a first preset condition;
[0167] A second acquisition unit, configured to acquire a predicted action of a target person at a target time based on the predicted motion trajectory;
[0168] The third acquisition unit is used to acquire a target action corresponding to the predicted action based on the target motion trajectory.
[0169] Optionally, the first preset condition includes any one of the following:
[0170] The first deviation is less than or equal to a first threshold;
[0171] The first deviation is greater than a second threshold;
[0172] The first threshold is smaller than the second threshold.
[0173] Optionally, the target motion trajectory includes multiple target trajectories, and different target trajectories correspond to different points;
[0174] Action Show 400 also includes:
[0175] A fifth acquisition module, used to acquire a second deviation between a predicted trajectory of a target point and a corresponding target trajectory, where the target point is any one of the multiple points;
[0176] The second display module is used to display the target point when the second deviation satisfies a second preset condition.
[0177] Optionally, the motion parameter information includes motion parameter information of the target person in a skiing scene.
[0178] The action display device 400 can realize the embodiment of the present application Figure 1 The various processes of the method embodiment and the same beneficial effects are achieved, and will not be described again here to avoid repetition.
[0179] The present application also provides an electronic device. Figure 1 The action display method shown is similar, so the implementation of the electronic device can refer to the implementation of the method, and the repeated parts will not be repeated. Figure 5 As shown, the electronic device of the embodiment of the present application includes a memory 520, a transceiver 510, and a processor 500;
[0180] The memory 520 is used to store computer programs; the transceiver 510 is used to send and receive data under the control of the processor 500; the processor 500 is used to read the computer program in the memory 520 and perform the following operations:
[0181] Obtain the motion parameter information of the target person;
[0182] Based on the motion parameter information, the motion trajectory of the target person is predicted to obtain the predicted motion trajectory;
[0183] Based on the predicted motion trajectory and the pre-acquired target motion trajectory, a predicted action of the target person at a target time and a target action corresponding to the predicted action are obtained;
[0184] Display the predicted and target actions.
[0185] Among them, Figure 5 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically linking various circuits of one or more processors represented by processor 500 and memory represented by memory 520. The bus architecture may also link various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 510 may be a plurality of components, namely, a transmitter and a transceiver, providing a unit for communicating with various other devices on a transmission medium. The processor 500 is responsible for managing the bus architecture and general processing, and the memory 520 may store data used by the processor 500 when performing operations.
[0186] The processor 500 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or a complex programmable logic device (CPLD). The processor may also adopt a multi-core architecture.
[0187] Optionally, based on the motion parameter information, the motion trajectory of the target person is predicted to obtain the predicted motion trajectory, including:
[0188] The motion parameter information is input into the motion trajectory prediction model to obtain the predicted motion trajectory of the target person;
[0189] Among them, the motion trajectory prediction model is trained using historical motion parameter information and historical motion trajectories.
[0190] Optionally, the motion trajectory prediction model includes multiple sub-prediction models, the motion parameter information includes motion parameter information of multiple points of the target person, and different sub-prediction models are used to predict the trajectories of different points of the target person;
[0191] The motion parameter information is input into the motion trajectory prediction model to obtain the predicted motion trajectory of the target person, including:
[0192] Inputting motion parameter information of each point in the multiple points into the corresponding sub-prediction model to obtain a predicted trajectory of each point;
[0193] Based on the predicted trajectories of multiple points, the predicted movement trajectory of the target person is determined.
[0194] Optionally, the motion parameter information includes at least one of the following:
[0195] Wind power;
[0196] wind direction;
[0197] The speed and direction of the target person as he or she leaves the first location;
[0198] The force-bearing area of the target person.
[0199] Optionally, the predicted action trajectory includes M first segmented trajectories, where M is a positive integer;
[0200] The processor 500 is further configured to read the computer program in the memory 520 and perform the following operations:
[0201] Obtaining M second segmented trajectories corresponding to the M first segmented trajectories in the target motion trajectory;
[0202] Matching each first segmented trajectory in the M first segmented trajectories with the corresponding second segmented trajectory, and determining a prediction score of each first segmented trajectory, where the prediction score is used to indicate a matching degree between the first segmented trajectory and the corresponding second segmented trajectory;
[0203] Based on the predicted scores of the M first segmented trajectories, the score of the target person is obtained, and the score of the target person is used to indicate the matching degree between the predicted motion trajectory and the target motion trajectory.
[0204] Optionally, based on the predicted motion trajectory and the pre-acquired target motion trajectory, the predicted action of the target person at the target time and the target action corresponding to the predicted action are acquired, including:
[0205] For each first segmented trajectory of the M first segmented trajectories, obtaining a first deviation between the first segmented trajectory and the corresponding second segmented trajectory;
[0206] The time of the target segmented trajectory among the M first segmented trajectories is taken as the target time, the target segmented trajectory is the segmented trajectory corresponding to the target deviation, and the target deviation is the deviation that satisfies the first preset condition among the M first deviations;
[0207] Based on the predicted motion trajectory, obtain the predicted action of the target person at the target time;
[0208] Based on the target motion trajectory, the target action corresponding to the predicted action is obtained.
[0209] Optionally, the first preset condition includes any one of the following:
[0210] The first deviation is less than or equal to a first threshold;
[0211] The first deviation is greater than a second threshold;
[0212] The first threshold is smaller than the second threshold.
[0213] Optionally, the target motion trajectory includes multiple target trajectories, and different target trajectories correspond to different points;
[0214] The processor 500 is further configured to read the computer program in the memory 520 and perform the following operations:
[0215] Obtaining a second deviation between a predicted trajectory of a target point and a corresponding target trajectory, where the target point is any one of the multiple points;
[0216] When the second deviation satisfies the second preset condition, the target point is displayed.
[0217] Optionally, the motion parameter information includes motion parameter information of the target person in a skiing scene.
[0218] The electronic device provided in the embodiment of the present application can perform the above Figure 1 The implementation principle and technical effect of the method embodiment shown are similar, and this embodiment will not be repeated here.
[0219] The embodiment of the present application also provides a readable storage medium on which a program or instruction is stored. When the program or instruction is executed by a processor, the above Figure 1The various processes of the method embodiment can achieve the same technical effect, and to avoid repetition, they will not be described here.
[0220] The processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0221] The present application also provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the above Figure 1 The various processes of the method embodiment can achieve the same technical effect, and to avoid repetition, they will not be described here.
[0222] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.
[0223] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.
[0224] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.
[0225] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.
Claims
1. An action display method, characterized in that: include: Obtain the motion parameter information of the target person; Based on the motion parameter information, predicting the motion trajectory of the target person to obtain a predicted motion trajectory; Based on the predicted motion trajectory and the pre-acquired target motion trajectory, acquiring a predicted action of the target person at a target time, and a target action corresponding to the predicted action; displaying the predicted action and the target action; The step of predicting the motion trajectory of the target person based on the motion parameter information to obtain the predicted motion trajectory includes: Inputting the motion parameter information into a motion trajectory prediction model to obtain a predicted motion trajectory of the target person; Wherein, the motion trajectory prediction model is obtained by training using historical motion parameter information and historical motion trajectory; The motion trajectory prediction model includes a plurality of sub-prediction models, the motion parameter information includes motion parameter information of a plurality of points of the target person, and different sub-prediction models are used to predict the trajectories of different points of the target person; The step of inputting the motion parameter information into a motion trajectory prediction model to obtain a predicted motion trajectory of the target person includes: Inputting the motion parameter information of each point in the plurality of points into the corresponding sub-prediction model to obtain a predicted trajectory of each point; Determining a predicted motion trajectory of the target person based on the predicted trajectories of the multiple points; The motion parameter information includes at least one of the following: Wind power; wind direction; The speed and direction of the target person when leaving the first location; The force-bearing area of the target person.
2. The method according to claim 1, characterized in that The predicted action trajectory includes M first segmented trajectories, where M is a positive integer; After predicting the motion trajectory of the target person based on the motion parameter information to obtain the predicted motion trajectory, the method further includes: Acquire M second segmented trajectories corresponding to the M first segmented trajectories in the target motion trajectory; Matching each first segmented trajectory in the M first segmented trajectories with the corresponding second segmented trajectory, and determining a prediction score of each first segmented trajectory, wherein the prediction score is used to indicate a matching degree between the first segmented trajectory and the corresponding second segmented trajectory; Based on the predicted scores of the M first segmented trajectories, a score of the target person is obtained, where the score of the target person is used to indicate a matching degree between the predicted motion trajectory and the target motion trajectory.
3. The method according to claim 2, characterized in that The step of acquiring the predicted action of the target person at the target time and the target action corresponding to the predicted action based on the predicted motion trajectory and the pre-acquired target motion trajectory includes: For each first segmented trajectory of the M first segmented trajectories, obtaining a first deviation between the first segmented trajectory and the corresponding second segmented trajectory; The time of the target segmented track among the M first segmented tracks is taken as the target time, the target segmented track is the segmented track corresponding to the target deviation, and the target deviation is the deviation that satisfies the first preset condition among the M first deviations; Based on the predicted motion trajectory, obtaining the predicted action of the target person at the target time; Based on the target motion trajectory, a target action corresponding to the predicted action is obtained.
4. The method according to claim 1, characterized in that The target motion trajectory includes multiple target trajectories, and different target trajectories correspond to different points; After inputting the motion parameter information of each of the multiple points into the corresponding sub-prediction model to obtain the predicted trajectory of each point, the method further includes: Obtaining a second deviation between a predicted trajectory of a target point and a corresponding target trajectory, wherein the target point is any one of the multiple points; When the second deviation satisfies a second preset condition, the target point is displayed.
5. The method according to claim 1, characterized in that The motion parameter information includes motion parameter information of the target person in a skiing scene.
6. An electronic device, characterized in that: It comprises a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the action display method as described in any one of claims 1 to 5 are implemented.
7. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps of the action display method according to any one of claims 1 to 5 are implemented.