A video processing method, electronic device and storage medium for five-a-side football

Abstract

The present invention provides a video processing method, electronic device and storage medium for five-a-side football, and relates to the field of data processing. The method comprises the following steps: obtaining a target video and a target user in the target video in real time, obtaining a target instruction issued by the target user most recently from a current time node, obtaining a target rule corresponding to the target instruction based on a preset instruction-rule correspondence relationship, obtaining a target time when the target user issues the target instruction based on the current time node and a preset compensation time, updating a remaining time based on the target rule and the target time, and displaying the remaining time on a preset screen. The present invention adopts a preset compensation time to correct a time difference between a target time when the target user issues the target instruction and a time difference inputted into the preset screen by a target professional user, thereby making the remaining time of the game more accurate.

Description

Technical Field

[0001] The invention relates to the field of data processing, and in particular to a video processing method, electronic equipment and storage medium for five-a-side football. Background Art

[0002] Futsal is a variation of indoor football, usually played on a smaller field. Each team has five players including the goalkeeper. A full game usually lasts two halves of 20 minutes each, with a short break in between. Some competitions also allow a one-minute timeout in each half. Compared to 11-a-side football, the field of futsal is smaller and the number of players is smaller.

[0003] In a five-a-side football match, various information about the game (remaining time, score, substitutions, number of fouls) is usually displayed on a large screen to ensure that the audience, players and coaching team can clearly understand the real-time game time and various information. The remaining time displayed on the large screen is usually input by the timekeeper, who operates according to the referee's instructions (such as the start of the game and the suspension of the game). However, there will be a certain error from the referee's instructions to the timekeeper's input of the remaining time, which will cause a certain error in the remaining time of the game. Summary of the invention

[0004] In view of the above technical problems, the technical solution adopted by the present invention is: a video processing method of five-a-side football, the method comprising the following steps:

[0005] S100, acquiring a target video and a target user in the target video in real time, wherein the target video is a video of an ongoing five-a-side football match;

[0006] S200, obtaining the target instruction issued by the target user most recently before the current time node;

[0007] S300, based on a preset instruction-rule correspondence relationship, obtaining a target rule corresponding to a target instruction;

[0008] S400, based on the current time node and the preset compensation time, obtaining the target time for the target user to issue the target instruction, wherein the preset compensation time is the time difference between the target user issuing the target instruction and the target professional user inputting the instruction into the preset screen;

[0009] S500, based on the target rule and the target time, the remaining time is updated and displayed on a preset screen.

[0010] According to another aspect of the present invention, a non-transitory computer-readable storage medium is provided, in which at least one instruction or at least one program is stored, and the at least one instruction or the at least one program is loaded and executed by a processor to implement the aforementioned method.

[0011] According to yet another aspect of the present invention, an electronic device is provided, comprising a processor and the aforementioned non-transitory computer-readable storage medium.

[0012] The present invention has at least the following beneficial effects:

[0013] In summary, the target video and the target user in the target video are obtained in real time, the target instruction of the target user most recently from the current time node is obtained, the target rule corresponding to the target instruction is obtained based on the preset instruction-rule correspondence, the target time when the target user issues the target instruction is obtained based on the current time node and the preset compensation time, the remaining time is updated based on the target rule and the target time, and the remaining time is displayed on a preset screen. The present invention adopts a preset compensation time to correct the time difference between the target time when the target user issues the target instruction and the time input into the preset screen by the target professional user, thereby making the remaining time of the game more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0015] Figure 1 The present invention provides a flowchart of a method for processing a five-a-side football video. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0017] An embodiment of the present invention provides a video processing method for five-a-side football, such as Figure 1 As shown, the method comprises the following steps:

[0018] S100, acquiring a target video and a target user in the target video in real time, wherein the target video is a video of an ongoing five-a-side football match.

[0019] Specifically, the target user is a referee of an ongoing five-a-side football match.

[0020] S200, obtaining the target instruction of the target user most recently from the current time node. It can be understood that the ongoing five-a-side football match is real-time, so the referee's instructions are issued in real time, and therefore the target instruction of the target user most recently from the current time node is obtained. Specifically, the target user's actions can be obtained by artificial observation or the like, thereby obtaining the target user's instructions, which is not limited by the present invention.

[0021] S300, based on a preset instruction-rule correspondence relationship, obtaining a target rule corresponding to a target instruction.

[0022] Specifically, the preset instruction-rule correspondence is the correspondence between the instruction made by the referee in the five-a-side football game and the rule corresponding to the instruction. For example, if the target user makes an instruction to pause for one minute, the corresponding target rule is that the five-a-side football game is paused for one minute.

[0023] S400, based on the current time node and the preset compensation time, obtaining the target time for the target user to issue the target instruction, wherein the preset compensation time is the time difference between the target user issuing the target instruction and the target professional user inputting it into the preset screen.

[0024] Specifically, the target professional user is a user who inputs the remaining time into the preset screen, and is generally a timekeeper. In addition, the present invention obtains the target time when the target user issues the target instruction based on the preset compensation time. It can be understood that there is a time difference between the target time when the target user issues the target instruction and the time when the target professional user inputs the preset screen. The time difference causes the display of the remaining time to be inaccurate, so the present invention uses the preset compensation time to correct the time difference.

[0025] S500, based on the target rule and the target time, the remaining time is updated and displayed on a preset screen.

[0026] In summary, the target video and the target user in the target video are obtained in real time, the target instruction of the target user most recently from the current time node is obtained, the target rule corresponding to the target instruction is obtained based on the preset instruction-rule correspondence, the target time when the target user issues the target instruction is obtained based on the current time node and the preset compensation time, the remaining time is updated based on the target rule and the target time, and the remaining time is displayed on a preset screen. The present invention adopts a preset compensation time to correct the time difference between the target time when the target user issues the target instruction and the time input into the preset screen by the target professional user, thereby making the remaining time of the game more accurate.

[0027] Specifically, in S400, the preset compensation time is obtained by the following steps:

[0028] S410, obtain the historical video list E = {E1, E2, ..., E j ,…,E n}, E j is the jth historical video, the value range of j is 1 to n, and n is the number of historical videos.

[0029] Specifically, the historical video is a video of a five-a-side football match that has ended.

[0030] S420, historical video E j Perform identification and obtain historical video E j History user's history command list C j ={C j1 , C j2 , …, C ji , …, C jm} and C j Corresponding historical video time node list B j = {B j1 , B j2 , …, B ji , …, B jm}, C ji is the i-th historical command issued by the historical user in the historical video, B ji It is C ji The time node of the historical video issued, the value of i ranges from 1 to m, and m is the number of historical commands issued by the historical user in the historical video.

[0031] Specifically, the historical video E is obtained through the neural network model j History user's history command list C j . And take the starting time node of Cji as the historical video time node B ji .

[0032] S430, obtaining a list of historical real time nodes D of historical instructions input by historical professional users j ={D j1 , D j2 , …, D ji , …, D jm}, D ji A history major user enters C ji Go to the time point of the history screen.

[0033] Specifically, the history professional user is a user who inputs the remaining time in the history video into the preset screen.

[0034] S440, obtaining a preset compensation time A0 = 1 / m × 1 / n × Σ n j＝1 Σ m i＝1 (D ji -B ji ).

[0035] In summary, obtain a list of historical videos, identify historical videos, obtain a list of historical commands of historical users in historical videos and a list of historical video time nodes, obtain a list of historical real time nodes when historical professional users input historical commands, obtain the preset compensation time, and use the average value of the errors in the historical data as the preset compensation time.

[0036] In another embodiment of the present invention, S400 further includes the following steps:

[0037] S401, obtain a training video list F = {F1, F2, ..., F r , …, F s}, F r is the rth training video, r ranges from 1 to s, and s is the number of training videos.

[0038] S402, training video F r Perform recognition and obtain training video F r List of training instructions for training users in G r = {G r，1 , G r，2 , …, G r，g , …, G r，zr} and G r The corresponding training video time node list H r ={H r，1 , H r，2 , …, H r，g , …, H r，zr}, G r，g Yes F r The gth training instruction issued by the training user, H r，g It's G r，g The training time node sent, the value range of g is 1 to zr, zr is F r The total number of training instructions issued by training users in .

[0039] S403, obtaining a training real time node list J of training instructions input by a professional training user r ={J r，1 , J r，2 , …, J r，g , …, J r，zr}, J r，gIt is the training professional user input G r，g The time point to the training screen.

[0040] S404, based on the training instruction list G r , training video time node list H r and the real time node list J for training r , get the training data list K = {K1, K2, ..., K x , …, K q}, classify the training data according to the training instructions, and obtain the category list set L = {L1, L2, ..., L t , …, L k}, where the training data K x =(G r，g ,H r，g ,J r，g ), the tth category L t ={L t，1 , L t，2 , …, L t，e , …, L t，ht}, L t，e =(L t1，e , L t2，e , L t3，e )∈K, where the training instructions in each category are the same.

[0041] L t，e is the e-th training data in the t-th category, t ranges from 1 to k, k is the number of categories, e ranges from 1 to ht, ht is the number of training data in the t-th category; where q = Σ s r＝1 zr=Σ k t＝1 ht. It can be understood that the training data with the same training instructions are classified into one category so that the training instructions of the training data in one category are the same. Specifically, it can be understood that L t1，e =G r，g , L t2,e =H r，g , L t3，e =J r，g .

[0042] S405, obtaining the category compensation time A of each category t =1 / ht×Σ ht e＝1 (L t3，e -L t2，e ).

[0043] Specifically, after S405 , the method further includes: based on the category corresponding to the target instruction, taking the category compensation time of the category corresponding to the target instruction as the preset compensation time.

[0044] In summary, a list of training videos is obtained, the training videos are identified, a list of training instructions for training users in the training videos and a list of corresponding training video time nodes are obtained, a list of training real time nodes for training instructions input by professional training users is obtained, a list of training data is obtained based on the list of training instructions, the list of training video time nodes and the list of training real time nodes, and the training data is classified according to the training instructions to obtain a set of category lists, and based on each category list, a category compensation time is obtained for each category; the category compensation time is calculated for each category, and under different training instructions, the time difference from when the training user sends the training instruction to the training real time node is different. Therefore, the present invention obtains the category compensation time under each training instruction and more accurately obtains the remaining time of the game.

[0045] Furthermore, after S500, when the five-a-side football game is over, the following steps are also included:

[0046] S001, obtaining a complete video, where the complete video is a whole video of a five-a-side football match.

[0047] S002, obtain the duration of the complete video.

[0048] S003, identify the complete video and obtain a list of participating users R = {R1, R2, ..., R c , …, R d}, R c is the cth participating user. The value range of c is 1 to d, and d is the number of participating users.

[0049] Specifically, users skilled in the art know that any method of identifying a person's portrait in a video in the prior art falls within the protection scope of the present invention and will not be described in detail here.

[0050] S004, traverse R, identify the complete video, and obtain the participating user R c List of preset behaviors for T c ={T c，1 , T c，2 ,…,T c，u ,…,T c，vc}, thereby obtaining a preset behavior list set T = {T1, T2, ..., T c ,…,T d}, T c，u The contestant is R cThe u-th preset behavior, u ranges from 1 to vc, vc is the value of the participating user R c The number of preset behaviors.

[0051] Specifically, the preset behavior list is a list of foul operations performed by participating users.

[0052] S005, obtain the command list U issued by the target user = {U1, U2, ..., U p , …, U f},U p is the pth instruction issued by the target user, the value range of p is 1 to f, and f is the number of instructions issued by the target user.

[0053] S006, generating an analysis report based on the duration of the complete video, the preset behavior list set T, and the instruction list U issued by the target user.

[0054] In summary, get the complete video, get the duration of the complete video, get the participating user R c The preset behavior list and the command list issued by the target user are used to generate an analysis report.

[0055] Furthermore, after S006, if the duration of the complete video does not belong to the preset game time period, the following steps are performed:

[0056] S061, obtain the actual difference ER=|Σ d c＝1 vc-f|. It can be understood that the actual difference is the number of times the target user misses or over-sends the target command.

[0057] Specifically, the preset competition time period is 45 minutes to 55 minutes in length.

[0058] S062, if the ER does not meet the preset difference rule, a first preset instruction is issued, and the first preset instruction is used to prompt the target user to verify. That is, if the duration of the complete video does not belong to the preset game time period, and when the actual difference does not meet the preset difference rule, it may be that there is a problem with the target user, and the target user is reminded to verify.

[0059] S063, if the ER meets the preset difference rule, a second preset instruction is issued, and the second preset instruction is used to prompt to verify the preset compensation time. If the duration of the complete video does not belong to the preset game time period, and when the actual difference meets the preset difference rule, it may be that there is a problem with the preset compensation time, and a prompt is given to verify the preset compensation time.

[0060] An embodiment of the present invention also provides a non-transitory computer-readable storage medium, which can be set in an electronic device to store at least one instruction or at least one program related to implementing a method in a method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement the method provided in the above embodiment.

[0061] An embodiment of the present invention further provides an electronic device, comprising a processor and the aforementioned non-transitory computer-readable storage medium.

[0062] Although some specific embodiments of the present invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present invention. It will also be appreciated by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the present invention. The scope of the present invention is defined by the appended claims.

Claims

1. A video processing method for five-a-side football, characterized in that: The method comprises the following steps: S100, acquiring a target video and a target user in the target video in real time, wherein the target video is a video of an ongoing five-a-side football match; S200, obtaining the target instruction issued by the target user most recently before the current time node; S300, based on a preset instruction-rule correspondence relationship, obtaining a target rule corresponding to a target instruction; S400, based on the current time node and the preset compensation time, obtaining the target time for the target user to issue the target instruction, wherein the preset compensation time is the time difference between the target user issuing the target instruction and the target professional user inputting the instruction into the preset screen; S500, based on the target rule and the target time, updating the remaining time, and displaying the remaining time on a preset screen; The preset compensation time in S400 is obtained by the following steps: S410, obtain a historical video list E={E1, E2, ..., E j ,…,E n }, E j is the jth historical video, where j ranges from 1 to n, and n is the number of historical videos, and the historical video is a video of a five-a-side football match that has ended; S420, historical video E j Perform identification and obtain historical video E j History user's history command list C j ={C j1 , C j2 , …, C ji , …, C jm } and C j Corresponding historical video time node list B j ={B j1 , B j2 , …, B ji , …, B jm }; C ji is the i-th historical command issued by the historical user in the historical video, B ji It is C ji The time node of the historical video issued, i ranges from 1 to m, and m is the number of historical commands issued by the historical user in the historical video; S430, obtaining a list of historical real time nodes D of historical instructions input by historical professional users j ={D j1 , D j2 , …, D ji , …, D jm }, D ji A history major user enters C ji Go to the time point of the history screen; S440, obtaining a preset compensation time A0=1 / m×1 / n×Σ n j=1 Σ m i=1 (D ji -B ji ).

2. The video processing method of five-a-side football according to claim 1, characterized in that: S400 also includes the following steps: S401, obtain a training video list F={F1, F2, ..., F r , …, F s }, F r is the rth training video, r ranges from 1 to s, and s is the number of training videos; S402, training video F r Perform recognition and obtain training video F r List of training instructions for training users in G r ={G r，1 , G r，2 , …, G r，g , …, G r，zr } and G r The corresponding training video time node list H r ={H r，1 , H r，2 , …, H r，g , …, H r，zr }, G r，g Yes F r The gth training instruction issued by the training user, H r，g It's G r，g The training time node sent, the value range of g is 1 to zr, zr is F r The total number of training instructions issued by the training users in; S403, obtaining a training real time node list J of training instructions input by a professional training user r ={J r，1 , J r，2 , …, J r，g , …, J r，zr }, J r，g It is the training professional user input G r，g The time to the training screen; S404, based on the training instruction list G r , training video time node list H r and the real time node list J for training r , get the training data list K={K1, K2, ..., K x , …, K q }, classify the training data according to the training instructions, and obtain the category list set L={L1, L2, ..., L t , …, L k }, where the training data K x =(G r，g,Hr，g,Jr，g ), the tth category L t ={L t，1 , L t，2 , …, L t，e , …, L t，ht }, L t，e =(L t1，e , L t2，e , L t3，e )∈K, where the training instructions in each category are the same; L t，e is the e-th training data in the t-th category, t ranges from 1 to k, k is the number of categories, e ranges from 1 to ht, ht is the number of training data in the t-th category; where q=Σ s r=1 zr=Σ k t=1 ht; S405, obtaining the category compensation time A of each category t =1 / ht×Σ ht e=1 (L t3，e -L t2，e ).

3. The video processing method of five-a-side football according to claim 2, characterized in that: After S405 , the method further includes: based on the category corresponding to the target instruction, taking the category compensation time of the category corresponding to the target instruction as the preset compensation time.

4. The video processing method of five-a-side football according to claim 1, characterized in that: Obtaining historical video E through neural network model j History user's history command list C j .

5. The video processing method of five-a-side football according to claim 1, characterized in that: After S500, when the five-a-side football game is over, the following steps are also included: S001, obtaining a complete video, where the complete video is a whole video of a five-a-side football match; S002, obtain the duration of the complete video; S003, identify the complete video and obtain the list of participating users R={R1, R2, …, R c , …, R d }, R c is the cth participating user, where c ranges from 1 to d, and d is the number of participating users; S004, traverse R, identify the complete video, and obtain the participating user R c List of preset behaviors for T c ={T c，1 , T c，2 ,…,T c，u ,…,T c，vc }, thereby obtaining the preset behavior list set T={T1, T2, …, T c ,…,T d }, T c，u The contestant is R c The u-th preset behavior, u ranges from 1 to vc, vc is the value of the participating user R c The number of preset behaviors; S005, obtain the command list U={U1, U2, ..., U p ,…,U f },U p is the pth instruction issued by the target user, the value range of p is 1 to f, and f is the number of instructions issued by the target user; S006, generating an analysis report based on the duration of the complete video, the preset behavior list set T, and the instruction list U issued by the target user.

6. The video processing method of five-a-side football according to claim 5, characterized in that: After S006, if the duration of the complete video does not belong to the preset game time period, the following steps are performed: S061, get the actual difference ER=|Σ d c=1 vc-f|; S062, if the ER does not satisfy the preset difference rule, issuing a first preset instruction, wherein the first preset instruction is used to prompt the target user to perform verification; S063: If ER satisfies the preset difference rule, a second preset instruction is issued, where the second preset instruction is used to prompt verification of the preset compensation time.

7. The video processing method of five-a-side football according to claim 6, characterized in that: The duration of the preset competition time period is 45 minutes to 55 minutes.

8. A non-transitory computer-readable storage medium, wherein at least one instruction or at least one program is stored in the storage medium, characterized in that: The at least one instruction or the at least one program is loaded and executed by the processor to implement the five-a-side football video processing method according to any one of claims 1 to 7.

9. An electronic device, characterized in that: The invention comprises a processor and the non-transitory computer-readable storage medium as claimed in claim 8.

Images