CN110933462A - Video processing method, system, electronic device and storage medium - Google Patents
Video processing method, system, electronic device and storage medium Download PDFInfo
- Publication number
- CN110933462A CN110933462A CN201910972416.2A CN201910972416A CN110933462A CN 110933462 A CN110933462 A CN 110933462A CN 201910972416 A CN201910972416 A CN 201910972416A CN 110933462 A CN110933462 A CN 110933462A
- Authority
- CN
- China
- Prior art keywords
- video
- slice
- original
- segment
- data
- 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.)
- Granted
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]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
- H04N21/845—Structuring of content, e.g. decomposing content into time segments
- H04N21/8456—Structuring of content, e.g. decomposing content into time segments by decomposing the content in the time domain, e.g. in time segments
-
- 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
- H04N21/2343—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements
-
- 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]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
- H04N21/4402—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving reformatting operations of video signals for household redistribution, storage or real-time display
Abstract
The present invention relates to the field of image processing, and in particular, to a video processing method, a video processing system, an electronic device, and a storage medium. The video processing method comprises the following steps: acquiring data of video characteristics of an original video; acquiring target video characteristics of each slice video segment forming the original video according to the data of the video characteristics; and packing the sliced video segments according to the target video characteristics. By adopting the embodiment of the invention, the whole video can be further finely classified according to the video content.
Description
Technical Field
The present invention relates to the field of image processing, and in particular, to a video processing method, a video processing system, an electronic device, and a storage medium.
Background
Video programs and the like watched by users on various platforms, wherein the video content of the video programs is usually fixed, in particular to video programs of movie and television series; users view the entire content included in each video program, and video operators generally view each produced video program as a separate entity.
However, the inventors found that the following problems exist in the related art: since the video content of a manufactured video program is usually fixed, it is difficult to perform further fine classification and re-editing on the fixed whole video content, and thus fine operation of the video content cannot be realized.
Disclosure of Invention
An object of embodiments of the present invention is to provide a video processing method, a video processing system, an electronic device, and a storage medium, which can further finely classify an entire video according to video contents.
To solve the above technical problem, an embodiment of the present invention provides a video processing method, including: acquiring data of video characteristics of an original video; acquiring target video characteristics of each slice video segment forming the original video according to the data of the video characteristics; and packing the sliced video segments according to the target video characteristics.
An embodiment of the present invention further provides a video processing system, including: the video feature extraction module is respectively connected with the video slice packaging module and the video feature management module, and the video slice packaging module is connected with the video feature management module; the video feature management module stores preset video features; the video feature extraction module is used for acquiring original video from a video source server, acquiring data of video features of the original video according to the preset video features, and sending the data of the video features to the video slice packaging module; the video slice packaging module is used for acquiring an original video from the video source server, slicing the original video to obtain slice video segments forming the original video, and acquiring target video characteristics of each slice video segment according to the data of the video characteristics; the video slice packaging module is further used for packaging the slice video segment according to the target video characteristics.
An embodiment of the present invention further provides a video processing system, including: the video feature extraction module is respectively connected with the video repacking module and the video feature management module, and the video repacking module is connected with the video feature management module; the video feature management module stores preset video features; the video feature extraction module is used for acquiring an original video from a preset decoder, acquiring data of video features of the original video according to the preset video features, and sending the data of the video features to the video repacking module; the original video is obtained by decoding a slice video segment which forms the original video through the decoder, and the slice video segment which forms the original video is prestored in a video source server; the video repackaging module is used for acquiring the sliced video segments forming the original video from the video source server, acquiring the target video characteristics of each sliced video segment according to the data of the video characteristics, and packing the sliced video segments according to the target video characteristics.
An embodiment of the present invention also provides an electronic device, 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 the video processing method described above.
Embodiments of the present invention also provide a computer-readable storage medium storing a computer program, which when executed by a processor implements the video processing method described above.
Compared with the prior art, the method and the device for obtaining the video feature data of the original video are obtained; acquiring target video characteristics of each slice video segment forming the original video according to the data of the video characteristics; and packing the sliced video segments according to the target video characteristics. It can be understood that the data of the video features can be used for representing video content, so that the original video is cut into a plurality of slice video segments, and the target video features of each slice video segment forming the original video are obtained according to the data of the video features of the original video, and the obtained target video features of each slice video segment represent the main content of each slice video segment, that is, the complete video is cut according to the video content; after the sliced video segments are packaged according to the target video characteristics, the main content in the video can be quickly obtained according to the target video characteristics of each sliced video segment, so that the video can be further classified in a refined manner according to different video contents, namely, a complete video can be subjected to refined operation according to the video contents; and the sliced video segments with different contents can be selectively provided for the user, so that the user can view the video in a personalized way.
In addition, acquiring data of video features of the original video includes: obtaining the confidence coefficient of a preset video characteristic in each preset time range of the original video; and taking the confidence coefficient of the preset video features in each preset time range as the data of the video features of the original video. The above provides a way to obtain data of video features of an original video, and at first, selectable video features in the original video are preset; since there may be a difference in the time when each video feature appears and the probability that each video feature is focused by the user in the original video, it is difficult to count the data of each video feature individually, so that the confidence of each preset video feature in each preset time range of the original video (the confidence reflects the probability that the video feature is focused by the user, and the higher the confidence, the more likely the video feature is focused by the user) is counted as the data of the video feature of the original video based on the time range as a division basis.
In addition, acquiring the target video characteristics of each slice video segment constituting the original video according to the data of the video characteristics includes: acquiring time length information of the sliced video segment; acquiring data of the alternative video characteristics of the sliced video segment according to the duration information of the sliced video segment and the preset time range; the data of the alternative video features comprise a plurality of confidence degrees of the preset video features in the preset time range; calculating target video characteristics of the slice video segment according to the data of the alternative video characteristics; the method for obtaining the target video characteristics of each sliced video segment is characterized in that the video characteristics included in the sliced video segment are obtained through the relation between the duration of the sliced video segment and the preset time range of the original video, and then the target video characteristics capable of representing the sliced video segment are screened out from the video characteristics included in the sliced video segment, so that the prominent content in the sliced video segment can be described simply.
In addition, the target video characteristics of the slice video segment are calculated by the following formula:
wherein the top (K) represents K target video features of the slice video segment; the m represents the data number of the alternative video features of the slice video band; the fin represents the confidence coefficient of the nth preset video feature in the data of the ith candidate video feature; the dn represents a preset weight of the nth preset video feature. The above-mentioned method for obtaining the target video features of the sliced video segment is provided, that is, the confidence of the video features (the confidence reflects the possibility that the video features are concerned by the user, and the higher the confidence, the more likely the video features are concerned by the user) and the weight of the preset video features (the weight reflects the operation requirement that the expected video features are concerned by the user, and the higher the weight, the more likely the operation expected video features are concerned by the user) are combined, and the K video features representing the content of the sliced video segment are calculated by the topK algorithm, so that the calculated K features can be concerned by the user, and can meet the operation requirement on the video content, thereby facilitating the fine operation of the whole video.
In addition, packing the sliced video segment according to the target video characteristics comprises: and writing the duration information of the slice video segment and the target video characteristics into a description file of the original video.
In addition, the section video segments forming the original video are prestored; the original video is obtained by the following method: and acquiring the slice video segment, and decoding the slice video segment to obtain an original video segment formed by the slice video segment. In consideration of the fact that in practical application, when a server issues a video, the video is generally cut into a plurality of video segments to be issued in sequence, so that if the existing stored video is a slice video segment, the slice video segment is restored to be a complete original video.
In addition, the method further comprises: and acquiring and returning a slice video segment containing video characteristics subscribed by the user from the packaged original video. Because the section video segment obtained by processing the original video according to the video content contains the information with representative video characteristics, the section video segment containing the subscribed video characteristics is returned to the user according to the subscription condition of the user to the video characteristics, so that the user can selectively watch the personalized and customized video content.
Drawings
One or more embodiments are illustrated by the corresponding figures in the drawings, which are not meant to be limiting.
Fig. 1 is a flowchart of a video processing method according to a first embodiment of the present invention;
fig. 2 is a flowchart of a manner of acquiring target video characteristics of each slice video segment according to the first embodiment of the present invention;
fig. 3 is a flowchart of a video processing method according to a second embodiment of the present invention;
fig. 4 is a block diagram showing the construction of a video processing system according to a third embodiment of the present invention;
fig. 5 is a block diagram showing the construction of a video processing system according to a fourth embodiment of the present invention;
fig. 6 is a block diagram showing the configuration of an electronic apparatus according to a fifth 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.
A first embodiment of the present invention relates to a video processing method, and a specific flow is shown in fig. 1, where the method includes:
102, acquiring target video characteristics of each slice video segment forming an original video according to the data of the video characteristics;
and 103, packing the sliced video segments according to the characteristics of the target video.
The following describes the implementation details of the video processing method of the present embodiment in detail, and the following only provides details for easy understanding and is not necessary to implement the present embodiment.
In step 101, data of video features of an original video is acquired. The original video in the embodiment is a complete video, and can be understood as an original video directly acquired from a camera shooting the original video; the video characteristics of the original video can be understood as representative characteristics in the video, such as a specific character, a specific building, a specific scene, and the like; the data of the video features can be understood as feature vectors obtained after image processing is performed on the video.
In this embodiment, a specific implementation of step 101, that is, a specific implementation method for acquiring data of video features of an original video, is provided, and includes:
(1) and obtaining the confidence coefficient of the preset video features in each preset time range of the original video.
Specifically, in order to meet the requirements of fine operation on video content and personalized watching of a user, N video features can be preset according to the video content of the original video; for example, a person a, a person B, a building a, a building B, a scene a, a scene B, etc. appearing in the video content of the original video can be one of the N preset video features. Since there may be a difference in the time of occurrence of each video feature in the original video and the probability of each video feature being focused on by the user due to the influence of the occurrence time, the occupied picture ratio, and the like, the confidence of each preset video feature in each preset time range of the original video is counted to reflect the probability of the preset video feature being focused on by the user in the preset time range, that is, the higher the confidence, the more likely the video feature is focused on by the user. In this embodiment, the dividing manner of each preset time range of the original video is not particularly limited, and the time lengths of each preset time range are not necessarily the same.
In one example, the preset video feature is < building a >, the confidence of < building a > in the first preset time range <1-3 seconds > of the original video is <0.9>, the confidence of < building a > in the second preset time range <3-9 seconds > is <0.5>, and the like are obtained.
It can be understood that the identification of the preset video features and the obtaining of the confidence of the preset video features can be implemented by an image identification processing algorithm and the like. For example, when the preset video feature is a human feature, specifically a certain star a, the confidence of the star a can be identified and obtained through a trained FaceNet model, and the FaceNet model is a deep learning face identification model; when the preset video features are building features, particularly a certain museum A, the confidence coefficient of the museum A can be identified and obtained through a trained YoLo model, and the YoLo model is a deep learning target identification model; when the preset video features are scene features, particularly fighting scenes, the confidence of the fighting scenes can be identified and obtained through the trained I3D model in combination with the frequency of scene switching and the like, and the I3D model is a deep learning behavior identification model.
(2) And taking the confidence coefficient of the preset video features in each preset time range as the data of the video features of the original video.
Specifically, taking a preset time range as a division basis, counting the confidence of each preset video feature in each preset time range, and taking the confidence as data of one video feature, the data can be expressed in the following form:
< time range t1, < feature 1, confidence ft11>, < feature 2, confidence ft12> … … < feature N, confidence ftnN > >; wherein N is the number of preset video features;
for example, <1-3 seconds, < building a, 0.9>, < person a, 0.5>, < building B, 0.3> … … < feature N, confidence ft1N > >. In practical application, the data of the video features can be serialized through processes such as protopuf or JSON, and converted into a form convenient for data processing.
In step 102, acquiring target video characteristics of each slice video segment forming the original video according to the data of the video characteristics; in this embodiment, a method for acquiring a target video feature of each slice video segment is provided, as shown in fig. 2, the method includes:
in step 201, time length information of a sliced video segment is obtained.
Specifically, in this embodiment, the original video obtained is a complete video, and the complete video is firstly sliced according to a preset slice size, where the preset slice size is not specifically limited, for example: slicing the original video once every 2 seconds or every 6 seconds or every 10 seconds; thus, after the original video is sliced, the time range actually covered by each sliced video segment can be obtained, for example: slicing the original video once every 10 seconds to obtain the time length information of the first sliced video segment as <0-10 seconds >, the time length information of the second sliced video segment as <10-20 seconds >, the time length information of the third sliced video segment as <20-30 seconds >, and the like. It is understood that in this step, the original video may be encoded by an encoder before the complete video is sliced, so as to compress the size of the original video for processing.
Specifically, since the data of the video features of the original video is divided according to the preset time range, the data in the time length information covered by the sliced video segment can be queried according to the preset time range of the original video as the data of the alternative video features of the sliced video segment. For example, the duration information of the first sliced video segment is <0-10 seconds >, and the data of the video characteristics of the original video includes: <1-3 seconds, < building a, 0.9>, < person a, 0.5>, < building B, 0.3> … … < feature N, confidence ft1N > >; <3-9 seconds, < person a, 0.9>, < building a, 0.5>, < building B, 0.3> … … < feature N, confidence ft2N > >; <9-12 seconds, < building B, 0.9>, < person a, 0.5>, < building a, 0.3> … … < feature N, confidence ft3N > >; the video feature data available in the first sliced video segment includes the following 3:
<1-3 seconds, < building a, 0.9>, < person a, 0.5>, < building B, 0.3> … … < feature N, confidence ft1N > >;
<3-9 seconds, < person a, 0.9>, < building a, 0.5>, < building B, 0.3> … … < feature N, confidence ft2N > >;
<9-10 seconds, < building B, 0.9>, < person a, 0.5>, < building a, 0.3> … … < feature N, confidence ft3N > >;
it will be appreciated that the acquired data of the alternative video feature of the sliced video segment may be represented in the form of:
< timeframe m, < signature 1, confidence value fm1>, < signature 2, confidence value fm2> … … < signature N, confidence value fmN > … … >;
and step 203, calculating the target video characteristics of the sliced video segments according to the data of the alternative video characteristics.
Specifically, considering that the target video features are required to be representative, the target video features can describe the highlighted content in the video in a simplified manner, and when the video is finely operated according to the target video features, the operation becomes complicated due to the excessive number of the target video features, so the number K of the target video features allowed by each slice of video segment can be preset, that is, the K target video features need to be calculated according to the data of the alternative video features, thereby avoiding the influence of the excessive target video features on the video operation.
In this embodiment, an implementation manner for calculating a target video feature is provided, and specifically, the target video feature is calculated by the following formula:
wherein the top (K) represents K target video features of the slice video segment; the m represents the data number of the alternative video features of the slice video band; the fin represents the confidence coefficient of the nth preset video feature in the data of the ith candidate video feature; and the dn represents the preset weight of the nth preset video characteristic, and N belongs to N. The topK algorithm used in this embodiment is an algorithm for quickly sorting and obtaining the top K bits, and the output finally obtained by the topK algorithm is K target video features of the slice video segment obtained by screening from the data of the candidate features.
The preset weight of the preset video feature refers to a weight preset for N video features preset according to video content of an original video, and each preset video feature corresponds to a preset weight; the larger the preset weight of the video feature is, the more the operator wants the video feature to be concerned by the user, that is, the operation intervention on the original video can be realized by setting the preset weight, and the operation requirement on the original video is reflected.
The algorithm for calculating the target video features combines the confidence coefficient of the video features (the confidence coefficient reflects the possibility that the video features are concerned by the user, and the higher the confidence coefficient is, the more likely the video features are concerned by the user) and the weight of the preset video features (the weight reflects the operation requirement that the expected video features are concerned by the user, and the higher the weight is, the more easily the operation expected video features are concerned by the user), and calculates the K video features representing the content of the slice video segment through the topK algorithm, so that the calculated K features can be concerned by the user, and can meet the operation requirement on the video content, thereby facilitating the fine operation of the whole video.
In step 103, the sliced video segment is packaged according to the target video characteristics. The embodiment provides a way for packing the sliced video segments, that is, writing the duration information and the target video characteristics of the sliced video segments into the description file of the original video; the description file in this embodiment may be understood as an HLS file or a DASH file, taking an HSL file as an example: hls (HTTP Live streaming) is a media streaming protocol based on HTTP, and is used for transmitting real-time audio and video; when the HLS protocol is used for sending the video, the whole video is cut into a small media file which can be downloaded through HTTP and a matched media file list, the client can pull the media file to play, and the playing effect is still the complete video; the original HLS file comprises a line of 'EXT-INF', and the value of the line of 'EXT-INF' is null, so that the time length information and the target video characteristics of the slice video segment can be written into the 'EXT-INF', and the original HLS file does not need to be modified in an extending mode. For example:
# EXT-INF 10.008, "< star a, star B, fighting >";
where "10.008" represents the time length information of the sliced video segment, which is approximately equal to the preset slice size (e.g., "slicing every 10 seconds" in step 201 in the present embodiment), the existence of the normal error may make the time length information not completely equal to the preset slice size (e.g., "10.008 seconds" here); "< star a, star B, fight >" indicates that the video segment of the slice contains video features < star a >, < star B > and < fight >.
In addition, after the sliced video segments are packaged, the sliced video segments containing the video characteristics subscribed by the user can be obtained and returned from the packaged original video according to the subscription condition of the user to the video characteristics. The N video characteristics are preset in advance according to the video content of the original video to meet the personalized watching requirement of the user, so that the preset N video characteristics can be provided for the user through the client before the video is played for the user to subscribe; if the user subscribes to all video features (namely subscribes to the whole video), the whole original video can be directly returned; if the user subscribes a plurality of characteristics in the N provided video characteristics, generating a slice video segment containing the video characteristics according to the description file of the original video and returning the slice video segment to the user; for example, if the user subscribes to the video feature < star a >, a sliced video segment containing < star a > is generated and returned to the user. It will be appreciated that the characteristics of the videos to which the user subscribes may be collected as user preference data to provide real-world data for the operation of the videos.
Compared with the prior art, the method and the device have the advantages that data of video characteristics of the original video are acquired; acquiring target video characteristics of each slice video segment forming the original video according to the data of the video characteristics; and packing the sliced video segments according to the target video characteristics. It can be understood that the data of the video features can be used for representing video content, so that the original video is cut into a plurality of sliced video segments, and the target video features of each sliced video segment constituting the original video are obtained according to the data of the video features of the original video, and the obtained target video features of each sliced video segment represent the main content of each sliced video segment, that is, the complete video is cut according to the video content; after the sliced video segments are packaged according to the target video characteristics, the main content in the video can be quickly obtained according to the target video characteristics of each sliced video segment, so that the video can be further classified in a refined manner according to different video contents, namely, a complete video can be subjected to refined operation according to the video contents; and the sliced video segments with different contents can be selectively provided for the user, so that the user can view the video in a personalized way.
A second embodiment of the present invention relates to a video processing method, and is substantially the same as the first embodiment except that the original video in the present embodiment is an original video restored by a sliced video segment; the flowchart of the video synthesizing method in this embodiment is similar to the flowchart shown in fig. 3, and includes:
In addition, after the sliced video segments are packaged, the sliced video segments containing the video features subscribed by the user can be obtained and returned from the packaged sliced video segments according to the subscription condition of the user to the video features. If the user subscribes to all video features (i.e. subscribes to the whole video), all sliced video segments can be directly returned; if the user subscribes to a plurality of characteristics in the N provided video characteristics, returning the slice video segment containing the video characteristics to the user according to the description file of the slice video segment; it will be appreciated that the video features subscribed to by the user may be collected as user preference data to provide real world data for the operation of the video.
In this embodiment, when data of video features of an original video is obtained, the original video needs to be decoded and restored according to a stored slice video segment; when the target video characteristics of each slice video segment are obtained, the original video restored by decoding does not need to be sliced; when the sliced video segment is packaged, writing the time length information and the target video characteristics of the sliced video segment into a description file of the sliced video segment; the embodiment provides a concrete implementation of another video processing method based on practical application.
The above examples in the present embodiment are for convenience of understanding, and do not limit the technical aspects of the present invention.
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 a video processing system, as shown in fig. 4, including: the video feature extraction module 401, the video slice packaging module 402 and the video feature management module 403, the video feature extraction module 401 is respectively connected with the video slice packaging module 402 and the video feature management module 403, and the video slice packaging module 402 is connected with the video feature management module 403; the video feature management module 403 stores preset video features;
the video feature extraction module 401 is configured to obtain an original video from a video source server, obtain data of video features of the original video according to the preset video features, and send the data of the video features to the video slice packaging module 402;
the video slice packaging module 402 is configured to obtain an original video from the video source server, slice the original video to obtain slice video segments constituting the original video, and obtain a target video feature of each slice video segment according to data of the video feature;
the video slice packing module 402 is further configured to pack the sliced video segment according to the target video characteristics.
It can be understood that the video slice packaging module 402 may be connected to the encoder 405, that is, the original video acquired by the video slice packaging module 402 from the video source server is encoded and compressed by the encoder 405, so that the size of the original video processed by the video slice packaging module 402 is small, which is helpful to shorten the processing time and improve the processing efficiency.
It can be understood that the video slice packaging module 402 is connected to a video source server 406 (e.g., a CDN origin server), the video source server 406 may be connected to a client 407, and the video slice packaging module 402 obtains an original video from the video source server 406 and sends a packaged slice video segment to the client 407 via the video source server 406 for a user to watch.
In one example, the video feature extraction module 401 obtains data of video features of an original video, including: obtaining the confidence coefficient of the preset video characteristics in each preset time range of the original video; and taking the confidence coefficient of the preset video features in each preset time range as the data of the video features of the original video.
In one example, the video slice packaging module 402 obtains the target video feature of each slice video segment constituting the original video according to the data of the video feature, including: acquiring time length information of the sliced video segment; acquiring data of the alternative video characteristics of the sliced video segments according to the duration information of the sliced video segments and the preset time range; wherein the data of the alternative video features comprises confidence degrees of the preset video features in a plurality of preset time ranges; and calculating the target video characteristics of the slice video segment according to the data of the alternative video characteristics.
In one example, the target video characteristics of the sliced video segment are calculated by the following formula:
wherein the top (K) represents K target video features of the slice video segment; the m represents the data number of the alternative video features of the slice video band; the fin represents the confidence coefficient of the nth preset video feature in the data of the ith candidate video feature; the dn represents a preset weight of the nth preset video feature.
In one example, the video slice packing module 402 packs the sliced video segment according to the target video characteristics, including: and writing the duration information of the slice video segment and the target video characteristics into a description file of the original video.
In one example, the video processing system further comprises: the personalized video module 404, the personalized video module 404 may be respectively connected to the video source server 406 and the client 407, and is configured to obtain, according to the video features subscribed by the user through the client 407, a slice video segment containing the video features subscribed by the user from the video source server 406, and return the slice video segment to the client 407; the video feature management module 403 is configured to provide the stored preset video features to the user for the user to subscribe to. In addition, the personalized video module 404 is further configured to collect video features subscribed by the user through the client 407 as user preference data to provide real data for the operation of the video.
It is to be understood that this embodiment is an example of an apparatus corresponding to the first embodiment, and this embodiment may be implemented in cooperation with the first embodiment, and details of related technologies mentioned in the first embodiment are still valid in this embodiment, and are not described herein again to reduce redundancy. Accordingly, the related-art details mentioned in the present embodiment can also be applied to the first embodiment.
A fourth embodiment of the present invention relates to a video processing system, as shown in fig. 5, including: the video feature extraction module 501, the video repacking module 502 and the video feature management module 503, wherein the video feature extraction module 501 is respectively connected with the video repacking module 502 and the video feature management module 503, and the video repacking module 502 is connected with the video feature management module 503; the video feature management module 503 stores preset video features;
the video feature extraction module 501 is connected to a preset decoder 505, and is configured to acquire an original video from the preset decoder 505, acquire data of video features of the original video according to the preset video features, and send the data of the video features to the video repacking module 502; the original video is obtained by decoding, by a decoder 505, a sliced video segment constituting the original video, where the sliced video segment constituting the original video is prestored in a video source server 506;
the video repackaging module 502 is configured to obtain slice video segments constituting the original video from the video source server 506, and obtain a target video feature of each slice video segment according to the data of the video feature; it is understood that the video repackaging module 502 can obtain the sliced video segment from the video source server 506 according to the received video source address, wherein the video source address can be sent from the video operator to the video repackaging module 502 in the video processing system.
The video repackaging module 502 is further configured to package the sliced video segment according to the target video characteristics.
It can be understood that the video repackaging module 502 is connected to the video source server 506 (e.g., CDN origin server), the video source server 506 may be connected to the client 507, and the video repackaging module 502 obtains the slice video segments constituting the original video from the video source server 506 and sends the packed slice video segments to the client 507 via the video source server 506 for the user to watch.
In one example, the video feature extraction module 501 obtains data of video features of an original video, including: obtaining the confidence coefficient of the preset video characteristics in each preset time range of the original video; and taking the confidence coefficient of the preset video features in each preset time range as the data of the video features of the original video.
In one example, the video repackaging module 502 obtains the target video characteristics of each slice video segment constituting the original video according to the data of the video characteristics, including: acquiring time length information of the sliced video segment; acquiring data of the alternative video characteristics of the sliced video segments according to the duration information of the sliced video segments and the preset time range; wherein the data of the alternative video features comprises confidence degrees of the preset video features in a plurality of preset time ranges; and calculating the target video characteristics of the slice video segment according to the data of the alternative video characteristics.
In one example, the target video characteristics of the sliced video segment are calculated by the following formula:
wherein the top (K) represents K target video features of the slice video segment; the m represents the data number of the alternative video features of the slice video band; the fin represents the confidence coefficient of the nth preset video feature in the data of the ith candidate video feature; the dn represents a preset weight of the nth preset video feature.
In one example, the video repackaging module 502 packetizes the sliced video segment according to the target video characteristics, including: and writing the time length information of the sliced video segment and the target video characteristics into a description file of the sliced video segment.
In one example, the video processing system further comprises: the personalized video module 504, the personalized video module 504 may be connected with the video source server 506 and the client 507 respectively, and is configured to obtain a sliced video segment containing video characteristics subscribed by the user from the video source server 506 according to the video characteristics subscribed by the user through the client 507, and return the sliced video segment to the client 507; the video feature management module 403 is configured to provide the stored preset video features to the user for the user to subscribe to. In addition, the method is also used for collecting video characteristics subscribed by the user through the client 507 as user preference data so as to provide real data for the operation of the video.
It is to be understood that this embodiment is an example of an apparatus corresponding to the second embodiment, and this embodiment may be implemented in cooperation with the second embodiment, and details of related technologies mentioned in the second embodiment are still valid in this embodiment, and are not described herein again to reduce redundancy. Accordingly, the related-art details mentioned in the present embodiment can also be applied to the second embodiment.
It should be noted that each module related in the third embodiment and the fourth embodiment is a logic module, and in practical application, one logic unit may be one physical unit, may be a part of one physical unit, and may be implemented by a combination of a plurality of 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 problem proposed by the present invention are not introduced in the present embodiment, but it does not indicate that other elements are not present in the present embodiment.
A fifth embodiment of the present invention relates to an electronic device, as shown in fig. 6, including at least one processor 601; and a memory 602 communicatively coupled to the at least one processor 601; the memory 602 stores instructions executable by the at least one processor 601, and the instructions are executed by the at least one processor 601 to enable the at least one processor 601 to execute the video processing method.
Where the memory 602 and the processor 601 are coupled in a bus, the bus may comprise any number of interconnected buses and bridges that couple one or more of the various circuits of the processor 601 and the memory 602 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 devices over a transmission medium. The data processed by the processor 601 is transmitted over a wireless medium via an antenna, which further receives the data and transmits the data to the processor 601.
The processor 601 is responsible for managing the bus and general processing and may also provide various functions including timing, peripheral interfaces, voltage regulation, power management, and other control functions. And the memory 602 may be used to store data used by the processor 601 in performing operations.
A sixth embodiment of the present invention relates to a computer-readable storage medium storing a computer program. The computer program, when executed by a processor, implements the above-described video processing method embodiments.
That is, as those skilled in the art can understand, all or part of the steps in the method of the embodiments described above may be implemented by a program to instruct 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, etc.) 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 of implementing 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 its practical application.
Claims (11)
1. A video processing method, comprising:
acquiring data of video characteristics of an original video;
acquiring target video characteristics of each slice video segment forming the original video according to the data of the video characteristics;
and packing the sliced video segments according to the target video characteristics.
2. The video processing method according to claim 1, wherein said obtaining data of video features of the original video comprises:
obtaining the confidence coefficient of a preset video characteristic in each preset time range of the original video;
and taking the confidence coefficient of the preset video features in each preset time range as the data of the video features of the original video.
3. The video processing method according to claim 2, wherein said obtaining the target video feature of each slice video segment constituting the original video according to the data of the video features comprises:
acquiring time length information of the sliced video segment;
acquiring data of the alternative video characteristics of the sliced video segment according to the duration information of the sliced video segment and the preset time range; the data of the alternative video features comprise confidence degrees of the preset video features in a plurality of preset time ranges;
and calculating the target video characteristics of the slice video segment according to the data of the alternative video characteristics.
4. The video processing method according to claim 3, wherein the target video characteristic of the sliced video segment is calculated by the following formula:
wherein the top (K) represents K target video features of the slice video segment; the m represents the data number of the alternative video characteristics of the slice video segment; the fin represents the confidence coefficient of the nth preset video feature in the data of the ith candidate video feature; the dn represents a preset weight of the nth preset video feature.
5. The video processing method according to claim 3, wherein said packaging the sliced video segment according to the target video characteristics comprises:
and writing the duration information of the slice video segment and the target video characteristics into a description file of the original video.
6. The video processing method according to claim 1, wherein a slice video segment constituting the original video is prestored; the original video is obtained by the following method:
and acquiring the slice video segment, and decoding the slice video segment to obtain an original video segment formed by the slice video segment.
7. The video processing method according to any one of claims 1 to 5, further comprising:
and acquiring and returning a slice video segment containing video characteristics subscribed by the user from the packaged original video.
8. A video processing system, comprising: the video feature extraction module is respectively connected with the video slice packaging module and the video feature management module, and the video slice packaging module is connected with the video feature management module; the video feature management module stores preset video features;
the video feature extraction module is used for acquiring an original video from a video source server, acquiring data of video features of the original video according to the preset video features, and sending the data of the video features to the video slice packaging module;
the video slice packaging module is used for acquiring an original video from the video source server, slicing the original video to obtain slice video segments forming the original video, and acquiring target video characteristics of each slice video segment according to the data of the video characteristics;
the video slice packaging module is further used for packaging the slice video segment according to the target video characteristics.
9. A video processing system, comprising: the video feature extraction module is respectively connected with the video repacking module and the video feature management module, and the video repacking module is connected with the video feature management module; the video feature management module stores preset video features;
the video feature extraction module is used for acquiring an original video from a preset decoder, acquiring data of video features of the original video according to the preset video features, and sending the data of the video features to the video repacking module; the original video is obtained by decoding a slice video segment which forms the original video through the decoder, and the slice video segment which forms the original video is prestored in a video source server;
the video repackaging module is used for acquiring the slice video segments forming the original video from the video source server and acquiring the target video characteristics of each slice video segment according to the data of the video characteristics;
the video repackaging module is further configured to package the sliced video segment according to the target video characteristics.
10. An electronic device, 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 video processing method of any of claims 1 to 7.
11. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out a video processing method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910972416.2A CN110933462B (en) | 2019-10-14 | 2019-10-14 | Video processing method, system, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910972416.2A CN110933462B (en) | 2019-10-14 | 2019-10-14 | Video processing method, system, electronic device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110933462A true CN110933462A (en) | 2020-03-27 |
| CN110933462B CN110933462B (en) | 2022-03-25 |
Family
ID=69848888
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910972416.2A Active CN110933462B (en) | 2019-10-14 | 2019-10-14 | Video processing method, system, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110933462B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160335499A1 (en) * | 2015-05-14 | 2016-11-17 | Google Inc. | Entity based temporal segmentation of video streams |
| CN108777815A (en) * | 2018-06-08 | 2018-11-09 | Oppo广东移动通信有限公司 | Method for processing video frequency and device, electronic equipment, computer readable storage medium |
| CN109922373A (en) * | 2019-03-14 | 2019-06-21 | 上海极链网络科技有限公司 | Method for processing video frequency, device and storage medium |
| CN110149531A (en) * | 2019-06-17 | 2019-08-20 | 北京影谱科技股份有限公司 | The method and apparatus of video scene in a kind of identification video data |
| CN110263217A (en) * | 2019-06-28 | 2019-09-20 | 北京奇艺世纪科技有限公司 | A kind of video clip label identification method and device |
-
2019
- 2019-10-14 CN CN201910972416.2A patent/CN110933462B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160335499A1 (en) * | 2015-05-14 | 2016-11-17 | Google Inc. | Entity based temporal segmentation of video streams |
| CN108777815A (en) * | 2018-06-08 | 2018-11-09 | Oppo广东移动通信有限公司 | Method for processing video frequency and device, electronic equipment, computer readable storage medium |
| CN109922373A (en) * | 2019-03-14 | 2019-06-21 | 上海极链网络科技有限公司 | Method for processing video frequency, device and storage medium |
| CN110149531A (en) * | 2019-06-17 | 2019-08-20 | 北京影谱科技股份有限公司 | The method and apparatus of video scene in a kind of identification video data |
| CN110263217A (en) * | 2019-06-28 | 2019-09-20 | 北京奇艺世纪科技有限公司 | A kind of video clip label identification method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110933462B (en) | 2022-03-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6469788B2 (en) | Using quality information for adaptive streaming of media content | |
| US10911809B2 (en) | Communication apparatus, communication method, and program | |
| KR20180105690A (en) | Communication device, communication control method, and computer program | |
| CN108282449B (en) | Streaming media transmission method and client applied to virtual reality technology | |
| WO2019184822A1 (en) | Multi-media file processing method and device, storage medium and electronic device | |
| WO2013173721A1 (en) | Audio-visual content delivery | |
| CN108881931B (en) | Data buffering method and network equipment | |
| US10924805B2 (en) | Methods and systems for content storage | |
| CN111526374B (en) | Live broadcast-based bullet screen processing method, stream pulling method and device | |
| KR101944601B1 (en) | Method for identifying objects across time periods and corresponding device | |
| US20160100132A1 (en) | Reception apparatus, reception method, and program thereof, image capturing apparatus, image capturing method, and program thereof, and transmission apparatus, transmission method, and program thereof | |
| CN110933462B (en) | Video processing method, system, electronic device and storage medium | |
| CN106937127B (en) | Display method and system for intelligent search preparation | |
| EP4052171A1 (en) | Image data segmentation and transmission | |
| WO2020137876A1 (en) | Generation device, three-dimensional data transmission device, and three-dimensional data reproduction device | |
| CN109587517B (en) | Multimedia file playing method and device, server and storage medium | |
| US20190227866A1 (en) | Information processing device and method | |
| CN112235592B (en) | Live broadcast method, live broadcast processing method, device and computer equipment | |
| US11936962B2 (en) | Information processing device and information processing method | |
| KR20230137459A (en) | Point cloud encoding method and apparatus, point cloud decoding method and apparatus, and computer-readable media, and electronic devices | |
| US11496535B2 (en) | Video data transmission apparatus, video data transmitting method, and storage medium | |
| CN108989905B (en) | Media stream control method and device, computing equipment and storage medium | |
| CN113411544A (en) | Video fragment file sending method and device, storage medium and electronic device | |
| CN114026875A (en) | Information processing apparatus, information processing method, reproduction processing apparatus, and reproduction processing method | |
| KR101637022B1 (en) | Apparatus and method for transmitting and receiving content |
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 |