CN110933459B - Event video clipping method, device, server and readable storage medium - Google Patents
Event video clipping method, device, server and readable storage medium Download PDFInfo
- Publication number
- CN110933459B CN110933459B CN201911126626.6A CN201911126626A CN110933459B CN 110933459 B CN110933459 B CN 110933459B CN 201911126626 A CN201911126626 A CN 201911126626A CN 110933459 B CN110933459 B CN 110933459B
- Authority
- CN
- China
- Prior art keywords
- decibel
- audio
- background
- change time
- time point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/233—Processing of audio elementary streams
Abstract
The embodiment of the invention relates to the technical field of multimedia, and discloses a method, a device, a server and a readable storage medium for editing an event video. In the invention, the method for editing the event video comprises the following steps: acquiring a pre-recorded event video, wherein the event video comprises a game audio; analyzing the match audio to obtain an explication audio and a background audio; determining an effective score change time point of the event video according to the commentary audio and the background audio; and editing the event video according to the effective score change time point. The invention also provides a clipping device, a server and a readable storage medium of the event video. The method, the device, the server and the readable storage medium for editing the event video can improve the editing efficiency and reduce the editing cost on the premise of ensuring the quality of the video editing.
Description
Technical Field
The embodiment of the invention relates to the technical field of multimedia, in particular to a method, a device, a server and a readable storage medium for editing an event video.
Background
With the development of internet technology, network videos are increasingly popular with users. To achieve a better user experience, video websites typically provide the functionality of video summary cues to guide the user in viewing. The video summary of the target video is used to indicate the highlight segments of the video in the target video. In the prior art, clipping a video file to obtain a video highlight is generally completed by manual operation, and even if some automatic clipping methods exist, the operations such as timing and quantification are still performed.
The inventor finds that at least the following problems exist in the prior art: the manual editing is long in time consumption, low in efficiency and high in labor cost, and the quality of the edited wonderful segments is not high through a simple timed and quantitative editing mode, so that the requirement of guiding the user to watch cannot be well met.
Disclosure of Invention
The invention aims to provide a method, a device, a server and a readable storage medium for clipping an event video, which can improve clipping efficiency and reduce clipping cost on the premise of ensuring the quality of a video clip.
In order to solve the above technical problem, an embodiment of the present invention provides a method for editing a video of an event, including the following steps: acquiring a pre-recorded event video, wherein the event video comprises a game audio; analyzing the match audio to obtain an explication audio and a background audio; determining an effective score change time point of the event video according to the commentary audio and the background audio; and editing the event video according to the effective score change time point.
The embodiment of the invention also provides a device for editing the event video, which comprises: the system comprises a video acquisition module, a video processing module and a video processing module, wherein the video acquisition module is used for acquiring a pre-recorded event video, and the event video comprises a match audio; the audio analysis module is used for analyzing the match audio to obtain an explanation audio and a background audio; an effective score change time point determining module, configured to determine an effective score change time point of the event video according to the commentary audio and the background audio; and the video clipping module is used for clipping the event video according to the effective score change time point.
An embodiment of the present invention further provides a server, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method of editing a video of an event as described above.
The embodiment of the invention also provides a computer readable storage medium, which stores a computer program, wherein the computer program is used for realizing the clipping method of the event video when being executed by a processor.
Compared with the prior art, the embodiment of the invention has the advantages that by acquiring the pre-recorded event video, wherein the event video comprises a game audio, the game audio is analyzed to obtain a comment audio and a background audio, determining an effective score change time point of the event video according to the commentary audio and the background audio, and according to the effective score change time point, the event video is edited, since the effective score change time point is obtained by analyzing the commentary audio and the background audio together, therefore, the effective score change time point is closer to the time point corresponding to the wonderful segment of the event, so that the event video is edited according to the effective ratio change time point, the quality of the video editing can be ensured, meanwhile, the manual continuous operation is not needed, so that the clipping efficiency is improved, and the clipping cost is reduced.
In addition, the determining, according to the commentary audio and the background audio, an effective score change time point of the event video specifically includes: determining a score change time point according to the commentary audio; obtaining the decibel number of the score change time point in the match audio as a score decibel number; acquiring decibels in the background audio as background decibels; and determining the effective score change time point of the event video from the score change time points according to the score decibels and the background decibels.
In addition, the determining an effective score change time point of the event video from the score change time points according to the score decibels and the background decibels specifically includes: acquiring background decibel reference numbers according to the background decibel numbers; and determining an effective score change time point of the event video from the score change time points according to the difference between the score decibel number and the background decibel reference number.
In addition, the obtaining of the background decibel reference number according to the background decibel number specifically includes: calculating the frequency of each decibel number in the background decibel numbers; and acquiring background decibel reference numbers according to the frequency of each decibel number. The background decibel reference number is obtained according to the frequency of each decibel number, data of large changes of the background decibel number caused by special factors can be screened out, and the obtained background decibel reference number is more accurate.
In addition, the obtaining of the background decibel reference number according to the frequency of each decibel number specifically includes: acquiring the first M decibels of the background decibels, wherein the frequency of the background decibels is from high to low; determining a decibel data section corresponding to each decibel number in the first M decibel numbers; calculating the frequency of the background decibel number distributed in each decibel data segment to obtain the decibel data segment with the maximum frequency; and determining the background decibel reference number according to the decibel data segment with the maximum frequency.
In addition, the determining a score change time point according to the commentary audio specifically includes: identifying the commentary audio to obtain score information; and determining a score change time point corresponding to the score information based on the score information.
In addition, the obtaining of the decibels in the background audio as the background decibels specifically includes: and acquiring the decibel number of the background audio every other preset time period as the background decibel number.
Drawings
One or more embodiments are illustrated by way of example in the accompanying drawings, which correspond to the figures in which like reference numerals refer to similar elements and which are not to scale unless otherwise specified.
FIG. 1 is a flow chart of a method for editing a video of an event according to a first embodiment of the present invention;
FIG. 2 is a flow diagram of sub-steps of step S13 of FIG. 1;
FIG. 3 is a flow chart of a method for editing a video of an event according to a second embodiment of the present invention;
FIG. 4 is a schematic structural diagram of an event video editing apparatus according to a third embodiment of the present invention;
fig. 5 is a schematic structural diagram of a server according to a fourth embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, it will be appreciated by those of ordinary skill in the art that numerous technical details are set forth in order to provide a better understanding of the present application in various embodiments of the present invention. However, the technical solution claimed in the present application can be implemented without these technical details and various changes and modifications based on the following embodiments.
The first embodiment of the invention relates to a method for editing an event video, and the specific flow is shown in fig. 1, and the method comprises the following steps:
and S11, acquiring the pre-recorded event video.
In this step, the server obtains a pre-recorded event video through networks such as WIFI, 2G/3G/4G/5G, and the like, where the event video includes a game audio and a picture synchronized with the audio, and the event video may be a sports event video such as a football, a basketball, a volleyball, and the like, and may also be an entertainment activity such as a phase sound, a small article, and the like, and this is not limited here.
And S12, analyzing the game audio to obtain the commentary audio and the background audio.
In this step, the match audio is analyzed, that is, the audio tracks contained in the match video are separated, and are distinguished according to the audio characteristics to obtain the commentary audio and the background audio, for example, a change curve of the background audio (for example, the background audio is a background song being played) is obtained, so that the background audio is removed from the match audio, and data of the commentary audio is obtained; or, according to the characteristics of the timbre of the commentator and the like, the sound of the commentator is separated from the game audio as the commentary audio, the rest audio in the game audio is used as the background audio, and the like, and the specific way of separating the commentary audio from the background audio is not limited herein.
And S13, determining the effective score change time point of the event video according to the commentary audio and the background audio.
Specifically, step S13 includes the following substeps:
s131: according to the commentary audio, a score change time point is determined.
In this step, the commentary audio may be recognized by a voice recognition method to obtain score information, and based on the score information, a score change time point corresponding to the score information is determined, for example, by recognizing keywords such as "score, a to B, where a and B are both numbers" and the like, so as to recognize the score information in the commentary audio, and record a time point corresponding to the score information as the score change time point, as shown in table 1:
| time of match | AB team score |
| 0:00:00 | 0:0 |
| 0:05:10 | 2:3 |
| 0:10:10 | 1:0 |
| 0:14:00 | 1:0 |
| 0:20:00 | 2:0 |
| 0:22:00 | 2:2 |
| 0:25:10 | 2:1 |
| 0:46:00 | 2:2 |
| 0:50:00 | 2:2 |
| 1:20:00 | 2:3 |
| 1:25:00 | 2:4 |
| 1:26:00 | 3:4 |
| 1:32:00 | 3:4 |
TABLE 1
S132: and acquiring the decibel number of the score change time point in the match audio as the score decibel number.
Specifically, the decibel number at each point of time of the score change in the game audio can be extracted as the score decibel number, as shown in table 2:
TABLE 2
S133: and acquiring the decibel number in the background audio as the background decibel number.
Specifically, the decibels of the background audio every other preset time period are obtained as background decibels, and the background decibels are generally integers, where the preset time period may be set according to actual requirements, for example, may be set to 30 seconds, 1 minute, two minutes, 5 minutes, and the like, for example, the decibel of the background audio every 1 minute is extracted as the background decibels, as shown in table 3:
| time of match | Decibel number |
| 0:00:00 | 60 |
| 0:01:00 | 51 |
| 0:02:00 | 48 |
| 0:03:00 | 52 |
| 0:04:00 | 49 |
| 0:05:10 | 48 |
| 0:06:00 | 54 |
| 0:07:00 | 50 |
| 0:08:00 | 47 |
| 0:09:00 | 55 |
| 0:10:10 | 80 |
| 0:11:00 | 74 |
| 0:12:00 | 59 |
| 0:13:00 | 52 |
| 0:14:00 | 55 |
| 0:15:00 | 47 |
| 0:16:00 | 46 |
| 0:17:00 | 48 |
| 0:18:00 | 50 |
| … | … |
TABLE 3
S134: and determining the effective score change time point of the event video from the score change time points according to the score decibels and the background decibels.
In this step, a background decibel reference number may be obtained according to the background decibel number, and then an effective score change time point of the event video may be determined from the score change time point according to a difference between the score decibel number and the background decibel reference number, that is, a decibel floating number.
The background decibel reference number can be obtained by calculating the frequency of each decibel number in the background decibel numbers and according to the frequency of each decibel number.
In practical application, the first M decibels with the frequency from high to low appearing in the background decibels are obtained, the decibel data section Di corresponding to each decibel in the first M decibels is determined, wherein Di is (Xi + a, Xi-b), Di is a data section corresponding to the ith decibel number in the first M decibel numbers, Xi is the ith decibel number in the first M decibel numbers, a is a first preset threshold value, b is a second preset threshold value, the frequency of the background decibel number distributed in each decibel data section is calculated, and the decibel data section Vmax (V (1), V (2) … V (i) … V (M)) with the maximum frequency is obtained, wherein V (i) is the frequency in the data section Di corresponding to the ith decibel number in the first M decibel numbers, and determining the background decibel reference number according to the decibel data segment Dmax with the maximum frequency.
In this embodiment, before determining the background decibel reference number according to the decibel data segment with the largest frequency of occurrence, the method may further include: judging whether the frequency Vmax of the decibel data segment with the maximum frequency is larger than or equal to a first frequency threshold value, if not, expanding the decibel data segment Di corresponding to each decibel number in the previous M decibel numbers, namely increasing a or b or increasing a and b simultaneously, and obtaining the frequency Vmax of the decibel data segment with the maximum frequency again until the frequency of the decibel data segment with the maximum frequency is larger than or equal to the first frequency threshold value. In this embodiment, the first frequency threshold may be 50%, and in practical applications, the first frequency threshold may be set as needed, and is not limited herein.
Optionally, after the frequency Vmax of the occurrence frequency of the decibel data segment with the largest occurrence frequency is greater than or equal to the first frequency threshold, the method further includes: the first P decibels with the highest frequency from high to low in the decibel data segment with the highest frequency are obtained, and the decibel data segment D corresponding to each decibel in the first P decibels is determinedi'and obtaining the frequency Vmax' Max (V (1) ', V (2)' … V (i) '… V (m)') of the newly appeared decibel data segment with the largest frequency, wherein Di’＝(Xi’+a’,Xi’-b’)，a’<a，b’<b，Di' is a data segment corresponding to the ith decibel number of the first P decibels,Xithe method comprises the steps of determining the frequency of an ith decibel data segment Di 'corresponding to the ith decibel number in the first P decibel numbers, determining the frequency of the data segment Di' corresponding to the ith decibel number in the first P decibel numbers, and judging whether the frequency of the decibel data segment with the maximum frequency is greater than or equal to a second frequency threshold value or not, if not, expanding the decibel data segment corresponding to each decibel number in the first P decibel numbers, and obtaining the frequency of the decibel data segment with the maximum frequency again until the frequency of the decibel data segment with the maximum frequency is greater than or equal to the second frequency threshold value, so that the range of the decibel data segment with the maximum frequency can be continuously refined, and the accuracy of the background decibel reference number is further improved.
In this embodiment, P is equal to M, and the first frequency threshold is equal to the first frequency threshold, but P may not be equal to M, and the first frequency threshold may not be equal to the first frequency threshold, which is not limited herein.
It should be noted that the above steps may be repeated until the difference between the frequency of the decibel data segment with the maximum frequency and the frequency of the decibel data segment with the second maximum frequency is greater than the fourth preset threshold, and the calculation is stopped, so as to ensure the accuracy of obtaining the background decibel reference number.
For example, in this embodiment, if the reference number of obtained background decibels is 50 decibels, the playing time, the AB team score, the score decibel number, and the decibel floating number are as shown in table 4:
| time of match | AB team score | Decibel number | Number of floating decibels |
| 0:00:00 | 0:0 | 60 | 10 |
| 0:10:10 | 1:0 | 80 | 30 |
| 0:14:00 | 1:0 | 55 | 5 |
| 0:20:00 | 2:0 | 78 | 28 |
| 0:25:10 | 2:1 | 81 | 31 |
| 0:46:00 | 2:2 | 56 | 6 |
| 0:50:00 | 2:2 | 85 | 35 |
| 1:20:00 | 2:3 | 78 | 28 |
| 1:25:00 | 2:4 | 75 | 25 |
| 1:26:00 | 3:4 | 84 | 34 |
| 1:32:00 | 3:4 | 60 | 10 |
TABLE 4
The commentator may predict the score, or mention the score of the last field of the participating team during the game, so that the same score may appear at different score change time points, and the cheering sound of the general scene and the voice of the commentator may appear in a greater decibel ratio than the general situation due to factors such as exciting at the wonderful moment such as goal score during the game, so that the time point corresponding to which score is the real score time point in the same score can be determined according to the size of the decibel floating number.
In the data in table 4, a score of 1:0 corresponds to two time points 0:10:10 and 0:14:00, the decibel fluctuation numbers are 30 and 5, respectively, the time point with the maximum decibel fluctuation number is 0:10:10, and meanwhile, the time point of 0:14:00 is eliminated, and so on, a score of 2:2, a score of 0:50:00, a score of 3:4, and a score of 1:26:00, and finally determined effective score change time points are as in table 4:
| time of match | AB team score | Decibel number | Number of floating decibels |
| 0:10:10 | 1:0 | 80 | 30 |
| 0:20:00 | 2:0 | 78 | 28 |
| 0:25:10 | 2:1 | 81 | 31 |
| 0:50:00 | 2:2 | 85 | 35 |
| 1:20:00 | 2:3 | 78 | 28 |
| 1:25:00 | 2:4 | 75 | 25 |
| 1:26:00 | 3:4 | 84 | 34 |
TABLE 5
And S14, editing the event video according to the effective score change time point.
Specifically, the video from the preset time before the effective ratio change time point to the effective ratio change time point can be edited to be used as the highlight, and then the highlight can be directly provided for the user to selectively watch, or the highlight is combined to be used as the video abstract, so that the user can quickly know the main content of the video, and the watching desire of the user on the complete video is increased.
Compared with the prior art, the embodiment of the invention has the advantages that by acquiring the pre-recorded event video, wherein the event video comprises a game audio, the game audio is analyzed to obtain a comment audio and a background audio, determining an effective score change time point of the event video according to the commentary audio and the background audio, and according to the effective score change time point, the event video is edited, since the effective score change time point is obtained by analyzing the commentary audio and the background audio together, therefore, the effective score change time point is closer to the time point corresponding to the wonderful segment of the event, so that the event video is edited according to the effective ratio change time point, the quality of the video editing can be ensured, meanwhile, the manual continuous operation is not needed, so that the clipping efficiency is improved, and the clipping cost is reduced.
A second embodiment of the invention relates to a method for editing a video of an event. The second embodiment is substantially the same as the first embodiment, and mainly differs therefrom in that: in the second embodiment of the present invention, determining a score change time point according to the commentary audio specifically includes: and determining a score change time point according to the commentary audio and the integral rule of the event, thereby removing some wrong score data and improving the accuracy of the video clip.
As shown in fig. 3, the method for editing an event video according to this embodiment includes the following steps:
and S21, acquiring the pre-recorded event video.
And S22, analyzing the game audio to obtain the commentary audio and the background audio.
S23: and determining a score change time point according to an integral rule for explaining the audio and the events.
Specifically, the commentary audio may be recognized by voice recognition to obtain score information, a time point corresponding to the score information may be determined based on the score information, score change information may be screened from the score information according to an integration rule of the event, and the time point corresponding to the score change information may be set as the score change time point. The manner of determining the time point corresponding to the score information is similar to that of the first embodiment, and details are not repeated here, and a specific manner of "screening the score variation information from the score information according to the integration rule of the event, and using the time point corresponding to the score variation information as the score variation time point" is illustrated below.
For example, for a football match, based on the rule that the score of the football is increased to one side every time, if the single-side jump exceeds 1, the time point is eliminated, and thus all the score change time points are judged and selected. In this step, the time points of the same score are all retained.
Specifically, assume that the time points corresponding to the score information are as in table 1, where the AB team score jumps from 0:0 to 2:3 from 0:00 to 0:05:10, and the single-side jump exceeds 1, so it can be determined that 2:3 is not the goal time point, and the time point 0:05:10 is removed; from 0:00:00 to 0:05:10, the AB team score jumps from 0:0 to 2:3, and the unilateral jump exceeds 1, so that the 2:3 is judged not to be the goal time point, and the time point of 0:05:10 is eliminated.
In the present embodiment, the score information and the score change time point obtained finally based on the score rule of the soccer game are shown in table 6:
table 6S 24: and acquiring the decibel number of the score change time point in the match audio as the score decibel number.
S25: and acquiring the decibel number in the background audio as the background decibel number.
S26: and determining the effective score change time point of the event video from the score change time points according to the score decibels and the background decibels.
And S27, editing the event video according to the effective score change time point.
In this embodiment, steps S21, S22, S24, S25, S26, and S27 are similar to steps S11, S12, S132, S133, S134, and S14, and thus are not described herein again.
Compared with the prior art, the embodiment of the invention has the advantages that by acquiring the pre-recorded event video, wherein the event video comprises a game audio, the game audio is analyzed to obtain a comment audio and a background audio, determining an effective score change time point of the event video according to the commentary audio and the background audio, and according to the effective score change time point, the event video is edited, since the effective score change time point is obtained by analyzing the commentary audio and the background audio together, therefore, the effective score change time point is closer to the time point corresponding to the wonderful segment of the event, so that the event video is edited according to the effective ratio change time point, the quality of the video editing can be ensured, meanwhile, the manual continuous operation is not needed, so that the clipping efficiency is improved, and the clipping cost is reduced; meanwhile, according to the comment audio and the integral rule of the event, the score change time point is determined, so that some wrong score data can be removed, and the accuracy of the video clip is improved.
The steps of the above methods are divided for clarity, and the implementation may be combined into one step or split some steps, and the steps are divided into multiple steps, so long as the same logical relationship is included, which are all within the protection scope of the present patent; it is within the scope of the patent to add insignificant modifications to the algorithms or processes or to introduce insignificant design changes to the core design without changing the algorithms or processes.
A third embodiment of the present invention relates to an event video editing apparatus, as shown in fig. 4, including: specifically, the video acquisition module 31 is configured to acquire a prerecorded event video, where the event video includes a game audio, the audio analysis module 32 is configured to analyze the game audio to obtain an explanation audio and a background audio, the effective score change time determination module 33 is configured to determine an effective score change time of the event video according to the explanation audio and the background audio, and the video clipping module 34 is configured to clip the event video according to the effective score change time.
It should be understood that this embodiment is an example of the apparatus corresponding to the first embodiment, and may be implemented in cooperation with the first embodiment. The related technical details mentioned in the first embodiment are still valid in this embodiment, and are not described herein again in order to reduce repetition. Accordingly, the related-art details mentioned in the present embodiment can also be applied to the first embodiment.
It should be noted that each module referred to in this embodiment is a logical module, and in practical applications, one logical unit may be one physical unit, may be a part of one physical unit, and may be implemented by a combination of multiple physical units. In addition, in order to highlight the innovative part of the present invention, elements that are not so closely related to solving the technical problems proposed by the present invention are not introduced in the present embodiment, but this does not indicate that other elements are not present in the present embodiment.
A fourth embodiment of the present invention relates to a server, as shown in fig. 5, including:
at least one processor 401; and the number of the first and second groups,
a memory 402 communicatively coupled to the at least one processor 401; wherein the content of the first and second substances,
the memory 402 stores instructions executable by the at least one processor 401 to enable the at least one processor 401 to perform the above-described method of recommending informational alerts of user top-up.
Where the memory 402 and the processor 401 are coupled by a bus, which may include any number of interconnected buses and bridges that couple one or more of the various circuits of the processor 401 and the memory 402 together. The bus may also connect various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface provides an interface between the bus and the transceiver. The transceiver may be one element or a plurality of elements, such as a plurality of receivers and transmitters, providing a means for communicating with various other apparatus over a transmission medium. The data processed by the processor 401 may be transmitted over a wireless medium via an antenna, which may receive the data and transmit the data to the processor 401.
The processor 401 is responsible for managing the bus and general processing and may provide various functions including timing, peripheral interfaces, voltage regulation, power management, and other control functions. And memory 402 may be used to store data used by processor 401 in performing operations.
A fifth embodiment of the present invention relates to a computer-readable storage medium storing a computer program. The computer program realizes the above-described method embodiments when executed by a processor.
That is, as can be understood by those skilled in the art, all or part of the steps in the method for implementing the embodiments described above may be implemented by a program instructing related hardware, where the program is stored in a storage medium and includes several instructions to enable a device (which may be a single chip, a chip, or the like) or a processor (processor) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It will be understood by those of ordinary skill in the art that the foregoing embodiments are specific examples for carrying out the invention, and that various changes in form and details may be made therein without departing from the spirit and scope of the invention in practice.
Claims (9)
1. A method for editing a video of an event, comprising:
acquiring a pre-recorded event video, wherein the event video comprises a game audio;
analyzing the match audio to obtain an explication audio and a background audio;
determining an effective score change time point of the event video according to the commentary audio and the background audio;
editing the event video according to the effective score change time point;
the determining an effective score change time point of the event video according to the commentary audio and the background audio specifically includes:
determining a score change time point according to the commentary audio;
obtaining the decibel number of the score change time point in the match audio as a score decibel number;
acquiring decibels in the background audio as background decibels;
and determining the effective score change time point of the event video from the score change time points according to the score decibels and the background decibels.
2. The method for editing an event video according to claim 1, wherein the determining the effective score change time point of the event video from the score change time points according to the score decibels and the background decibels specifically comprises:
acquiring background decibel reference numbers according to the background decibel numbers;
and determining an effective score change time point of the event video from the score change time points according to the difference between the score decibel number and the background decibel reference number.
3. The method for editing a game video according to claim 2, wherein the obtaining a background decibel reference number according to the background decibel number specifically comprises:
calculating the frequency of each decibel number in the background decibel numbers;
and acquiring background decibel reference numbers according to the frequency of each decibel number.
4. The method for editing a game video according to claim 3, wherein the obtaining a background decibel reference number according to the frequency of occurrence of each decibel number specifically comprises:
acquiring the first M decibels of the background decibels, wherein the frequency of the background decibels is from high to low;
determining a decibel data section corresponding to each decibel number in the first M decibel numbers;
calculating the frequency of the background decibel number distributed in each decibel data segment to obtain the decibel data segment with the maximum frequency;
and determining the background decibel reference number according to the decibel data segment with the maximum frequency.
5. The method for clipping a game video according to claim 1, wherein the determining a score change time point according to the commentary audio includes:
identifying the commentary audio to obtain score information;
and determining a score change time point corresponding to the score information based on the score information.
6. The method for editing an event video according to claim 1, wherein the obtaining the decibels in the background audio as background decibels specifically comprises:
and acquiring the decibel number of the background audio every other preset time period as the background decibel number.
7. An apparatus for editing a video of an event, comprising:
the system comprises a video acquisition module, a video processing module and a video processing module, wherein the video acquisition module is used for acquiring a pre-recorded event video, and the event video comprises a match audio;
the audio analysis module is used for analyzing the match audio to obtain an explanation audio and a background audio;
an effective score change time point determining module, configured to determine an effective score change time point of the event video according to the commentary audio and the background audio;
the video clipping module is used for clipping the event video according to the effective score change time point;
the effective score change time point determining module is specifically configured to determine a score change time point according to an explanation audio, obtain a decibel number of the score change time point in the game audio as a score decibel number, obtain a decibel number in the background audio as a background decibel number, and determine the effective score change time point of the game video from the score change time point according to the score decibel number and the background decibel number.
8. A server, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of clipping a video of an event according to any one of claims 1 to 6.
9. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out a method of clipping a video of an event according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911126626.6A CN110933459B (en) | 2019-11-18 | 2019-11-18 | Event video clipping method, device, server and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911126626.6A CN110933459B (en) | 2019-11-18 | 2019-11-18 | Event video clipping method, device, server and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110933459A CN110933459A (en) | 2020-03-27 |
| CN110933459B true CN110933459B (en) | 2022-04-26 |
Family
ID=69854065
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911126626.6A Active CN110933459B (en) | 2019-11-18 | 2019-11-18 | Event video clipping method, device, server and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110933459B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111491176B (en) * | 2020-04-27 | 2022-10-14 | 百度在线网络技术（北京）有限公司 | Video processing method, device, equipment and storage medium |
| CN113537052B (en) * | 2021-07-14 | 2023-07-28 | 北京百度网讯科技有限公司 | Video clip extraction method, device, equipment and storage medium |
| CN115103222A (en) * | 2022-06-24 | 2022-09-23 | 湖南快乐阳光互动娱乐传媒有限公司 | Video audio track processing method and related equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006129363A (en) * | 2004-11-01 | 2006-05-18 | Casio Comput Co Ltd | Program summary apparatus and program summary processing program |
| CN101599179A (en) * | 2009-07-17 | 2009-12-09 | 北京邮电大学 | Method for automatically generating field motion wonderful scene highlights |
| JP2011029938A (en) * | 2009-07-24 | 2011-02-10 | Toshiba Corp | Video server and highlight scene editing method |
| CN102427507A (en) * | 2011-09-30 | 2012-04-25 | 北京航空航天大学 | Football video highlight automatic synthesis method based on event model |
| CN104992712A (en) * | 2015-07-06 | 2015-10-21 | 成都云创新科技有限公司 | Music reorganization-based music score automatic formation method |
| CN105912560A (en) * | 2015-02-24 | 2016-08-31 | 泽普实验室公司 | Detect sports video highlights based on voice recognition |
| CN108833969A (en) * | 2018-06-28 | 2018-11-16 | 腾讯科技（深圳）有限公司 | A kind of clipping method of live stream, device and equipment |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB9206651D0 (en) * | 1992-03-26 | 1992-05-06 | Solid State Logic Ltd | Video processing |
| JP3973572B2 (en) * | 2003-02-07 | 2007-09-12 | 日本電信電話株式会社 | Data analysis apparatus and data analysis program |
| CN102263907B (en) * | 2011-08-04 | 2013-09-18 | 央视国际网络有限公司 | Play control method of competition video, and generation method and device for clip information of competition video |
| GB201310861D0 (en) * | 2013-06-18 | 2013-07-31 | Nokia Corp | Audio signal analysis |
| US9699523B1 (en) * | 2014-09-08 | 2017-07-04 | ProSports Technologies, LLC | Automated clip creation |
| JP2016107001A (en) * | 2014-12-10 | 2016-06-20 | 富士通株式会社 | Extraction program, method, and device |
| US10362340B2 (en) * | 2017-04-06 | 2019-07-23 | Burst, Inc. | Techniques for creation of auto-montages for media content |
| CN109344292B (en) * | 2018-09-28 | 2022-04-22 | 百度在线网络技术（北京）有限公司 | Method, device, server and storage medium for generating event score segments |
-
2019
- 2019-11-18 CN CN201911126626.6A patent/CN110933459B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006129363A (en) * | 2004-11-01 | 2006-05-18 | Casio Comput Co Ltd | Program summary apparatus and program summary processing program |
| CN101599179A (en) * | 2009-07-17 | 2009-12-09 | 北京邮电大学 | Method for automatically generating field motion wonderful scene highlights |
| JP2011029938A (en) * | 2009-07-24 | 2011-02-10 | Toshiba Corp | Video server and highlight scene editing method |
| CN102427507A (en) * | 2011-09-30 | 2012-04-25 | 北京航空航天大学 | Football video highlight automatic synthesis method based on event model |
| CN105912560A (en) * | 2015-02-24 | 2016-08-31 | 泽普实验室公司 | Detect sports video highlights based on voice recognition |
| CN104992712A (en) * | 2015-07-06 | 2015-10-21 | 成都云创新科技有限公司 | Music reorganization-based music score automatic formation method |
| CN108833969A (en) * | 2018-06-28 | 2018-11-16 | 腾讯科技（深圳）有限公司 | A kind of clipping method of live stream, device and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110933459A (en) | 2020-03-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110933459B (en) | Event video clipping method, device, server and readable storage medium | |
| US7424204B2 (en) | Video information summarizing apparatus and method for generating digest information, and video information summarizing program for generating digest information | |
| CN110650374B (en) | Clipping method, electronic device, and computer-readable storage medium | |
| CN101483767B (en) | Method and apparatus for recording and playing back content data | |
| US9736432B2 (en) | Identifying popular network video segments | |
| EP1067800A1 (en) | Signal processing method and video/voice processing device | |
| EP2916557A1 (en) | Display apparatus and control method thereof | |
| CN110602550A (en) | Video processing method, electronic equipment and storage medium | |
| CN106658226B (en) | Playing method and device | |
| JP2010523068A (en) | How to determine a point in time in an audio signal | |
| CN106851394A (en) | A kind of background music switching method and apparatus | |
| CN112511854A (en) | Live video highlight generation method, device, medium and equipment | |
| WO2011066432A9 (en) | System and method for uploading and downloading a video file and synchronizing videos with an audio file | |
| US20230217049A1 (en) | Intelligent download of content | |
| JP2000285243A (en) | Signal processing method and video sound processing device | |
| CN113347489B (en) | Video clip detection method, device, equipment and storage medium | |
| CN101799823A (en) | Contents processing apparatus and method | |
| CN104796732B (en) | A kind of audio and video edit methods and device | |
| US9959298B2 (en) | Method, apparatus and system for indexing content based on time information | |
| JP4293105B2 (en) | Information processing apparatus and method, and program | |
| WO2011161820A1 (en) | Video processing device, video processing method and video processing program | |
| CN112597335A (en) | Output device and output method for selecting section of opera | |
| KR101434783B1 (en) | Scene fragment transmitting system, scene fragment trasnmitting method and recording medium | |
| CN107493481A (en) | Video broadcasting method and device based on virtual video technology | |
| WO2012029252A1 (en) | Information processing apparatus, information processing method, and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |