CN111629261B - Information processing method, information processing device, electronic equipment and computer readable storage medium - Google Patents

Information processing method, information processing device, electronic equipment and computer readable storage medium Download PDF

Info

Publication number
CN111629261B
CN111629261B CN201910153264.3A CN201910153264A CN111629261B CN 111629261 B CN111629261 B CN 111629261B CN 201910153264 A CN201910153264 A CN 201910153264A CN 111629261 B CN111629261 B CN 111629261B
Authority
CN
China
Prior art keywords
screenshot
video data
key frame
target video
mode
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
Application number
CN201910153264.3A
Other languages
Chinese (zh)
Other versions
CN111629261A (en
Inventor
丁一
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Alibaba Group Holding Ltd
Original Assignee
Alibaba Group Holding Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Alibaba Group Holding Ltd filed Critical Alibaba Group Holding Ltd
Priority to CN201910153264.3A priority Critical patent/CN111629261B/en
Publication of CN111629261A publication Critical patent/CN111629261A/en
Application granted granted Critical
Publication of CN111629261B publication Critical patent/CN111629261B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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]
    • H04N21/40—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 or rendering scenes according to encoded video stream scene graphs
    • H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
    • 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
    • H04N21/21—Server components or server architectures
    • H04N21/218—Source of audio or video content, e.g. local disk arrays
    • H04N21/2187—Live feed
    • 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
    • H04N21/433—Content storage operation, e.g. storage operation in response to a pause request, caching operations
    • H04N21/4334—Recording operations
    • 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
    • H04N21/84—Generation or processing of descriptive data, e.g. content descriptors
    • H04N21/8405—Generation or processing of descriptive data, e.g. content descriptors represented by keywords

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Television Signal Processing For Recording (AREA)

Abstract

The embodiment of the disclosure discloses an information processing method, an information processing device, an electronic device and a computer readable storage medium, wherein the method comprises the following steps: determining an interval between two key frames in the target video data; and selecting one of a key frame screenshot mode and a non-key frame screenshot mode according to the interval to obtain the video frame information in the target video data. According to the technical scheme, balance can be achieved in cost and benefit, and video content in target video data is not omitted to the maximum extent while cost waste is avoided.

Description

Information processing method, information processing device, electronic equipment and computer readable storage medium
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to an information processing method and apparatus, an electronic device, and a computer-readable storage medium.
Background
With the development of internet technology, video resources published on the network are more and more abundant, especially, live videos are more and more in recent two years, and in view of the requirements of video supervision and audit, the identification and audit specifications of live videos are strict. In general, to make a strict audit, a non-key frame screenshot mode of one frame per 1 second is adopted to capture video frames from a live video stream and perform the audit. However, the non-key frame screenshot mode has a large machine overhead for screenshot service, that is, the cost is high; the resolution and frame rate of the stream are two key indicators for determining the cost. Therefore, how to balance the auditing effect and the cost is one of the difficulties in auditing the video stream.
Disclosure of Invention
The embodiment of the disclosure provides an information processing method and device, electronic equipment and a computer readable storage medium.
In a first aspect, an embodiment of the present disclosure provides an information processing method.
Specifically, the information processing method includes:
determining the interval between two key frames in the target video data;
and selecting one of a key frame screenshot mode and a non-key frame screenshot mode according to the interval to obtain the video frame information in the target video data.
Further, before determining the interval between two key frames in the target video data, the method further includes:
obtaining a pre-review result of the target video data; the pre-auditing result comprises a target screenshot mode of the target video data; the target screenshot mode includes one of a key frame screenshot mode, a non-key frame screenshot mode, and an adaptive screenshot mode.
Further, the determining the interval between two key frames in the target video data includes:
and when the target screenshot mode is the self-adaptive adjustment mode, determining the interval between two key frames in the target video data.
Further, the pre-review result further comprises a screenshot period.
Further, according to the interval, one of a key frame screenshot mode and a non-key frame screenshot mode is selected to obtain video frame information in the target video data, and the method includes at least one of the following steps:
when the interval is larger than the screenshot period, acquiring the video frame information in the target video data by adopting a key frame screenshot mode;
and when the interval is less than or equal to the screenshot period, acquiring the video frame information in the target video data by adopting a non-key frame screenshot mode.
Further, determining an interval between two key frames in the target video data comprises:
and acquiring video frame information in the target video data by adopting a non-key frame screenshot mode, and determining the interval according to the video frame information.
Further, the method further comprises at least one of:
when the target screenshot mode is a key frame screenshot mode, intercepting key frame information from the target video data acquired in real time according to the screenshot period;
and when the target screenshot mode is a non-key frame screenshot mode, intercepting non-key frame information from the target video data acquired in real time according to the screenshot period.
Further, the method further comprises: and auditing the target video data according to the video frame information.
Further, the method further comprises:
and adjusting the target screenshot mode of the target video data according to the auditing result of the target video data.
In a second aspect, an embodiment of the present disclosure provides an information processing apparatus.
Specifically, the information processing apparatus includes:
a first determining module configured to determine an interval between two key frames in target video data;
and the first acquisition module is configured to select one of a key frame screenshot mode and a non-key frame screenshot mode according to the interval to acquire the video frame information in the target video data.
Further, before the first determining module, the method further includes:
the second acquisition module is configured to acquire a pre-review result of the target video data; the pre-auditing result comprises a target screenshot mode of the target video data; the target screenshot mode includes one of a key frame screenshot mode, a non-key frame screenshot mode, and an adaptive screenshot mode.
Further, the first determining module includes:
and the determining sub-module is configured to determine the interval between two key frames in the target video data when the target screenshot mode is the adaptive adjustment mode.
Further, the pre-review result further comprises a screenshot period.
Further, the first obtaining module includes at least one of:
a first obtaining sub-module configured to obtain the video frame information in the target video data in a key frame screenshot mode when the interval is greater than the screenshot period;
a second obtaining sub-module configured to obtain the video frame information in the target video data in a non-key frame screenshot mode when the interval is less than or equal to the screenshot period.
Further, the first determining module includes:
and the third acquisition sub-module is configured to acquire video frame information in the target video data in a non-key frame screenshot mode and determine the interval according to the video frame information.
Further, the apparatus further comprises at least one of:
the first intercepting module is configured to intercept key frame information from the target video data acquired in real time according to the screenshot period when the target screenshot mode is a key frame screenshot mode;
and the second intercepting module is configured to intercept non-key frame information from the target video data acquired in real time according to the screenshot period when the target screenshot mode is a non-key frame screenshot mode.
Further, the apparatus further comprises:
and the auditing module is configured to audit the target video data according to the video frame information.
Further, the apparatus further comprises:
and the adjusting module is configured to adjust the target screenshot mode of the target video data according to the auditing result of the target video data.
The functions can be realized by hardware, and the functions can also be realized by executing corresponding software by hardware. The hardware or software includes one or more modules corresponding to the above-described functions.
In one possible design, the information processing apparatus includes a memory and a processor, the memory is used for storing one or more computer instructions for supporting the information processing apparatus to execute the information processing method in the fourth to sixth aspects, and the processor is configured to execute the computer instructions stored in the memory. The information processing apparatus may further include a communication interface for the information processing apparatus to communicate with other devices or a communication network.
In a third aspect, an embodiment of the present disclosure provides an electronic device, including a memory and a processor; wherein the memory is configured to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method of the first aspect.
In a fourth aspect, the disclosed embodiments provide a computer-readable storage medium for storing computer instructions for a security authentication apparatus for an enterprise account, which includes computer instructions for performing the information processing method in the first aspect.
The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:
according to the method and the device, when the screenshot mode of the target video data is determined to be the self-adaptive adjustment mode, whether the target screenshot mode is the key frame screenshot mode or the non-key frame screenshot mode is determined according to the interval between two key frames in the target video data. By the method, the key frame screenshot mode or the non-key frame screenshot mode can be adaptively selected according to the interval between the two key frames in the target video data to acquire the video frame information from the target video data, so that balance can be achieved in cost and benefit, and the video content in the target video data is not omitted to the greatest extent while the cost waste is avoided.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
Other features, objects, and advantages of the present disclosure will become more apparent from the following detailed description of non-limiting embodiments when taken in conjunction with the accompanying drawings. In the drawings:
FIG. 1 is a schematic structural diagram of a video review system according to an embodiment of the present disclosure;
FIG. 2 shows a flow diagram of an information processing method according to an embodiment of the present disclosure;
fig. 3 is a schematic diagram showing a composition structure of a GOP in video information;
fig. 4 shows a block diagram of the structure of an information processing apparatus according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of an electronic device suitable for implementing an information processing method according to an embodiment of the present disclosure.
Detailed Description
Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. Also, for the sake of clarity, parts not relevant to the description of the exemplary embodiments are omitted in the drawings.
In the present disclosure, it is to be understood that terms such as "including" or "having," etc., are intended to indicate the presence of the disclosed features, numbers, steps, behaviors, components, parts, or combinations thereof, and are not intended to preclude the possibility that one or more other features, numbers, steps, behaviors, components, parts, or combinations thereof may be present or added.
It should be further noted that the embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Fig. 1 is a schematic structural diagram of a video auditing system according to an embodiment of the present disclosure. As shown in fig. 1, a user performs live video broadcast through a terminal 101, the terminal 101 sends the live video of the user to a platform server 102, the platform server 102 sends the video to a video auditing server 103 for auditing, and if the video is live video broadcast, the platform server 102 pushes a video stream to the video auditing server 103 in real time; the video review server 103 may include a pre-review decision unit 1031, a screenshot service unit 1032, and an review service unit 1033. The pre-audit decision unit 1031 may pre-audit the video stream, and output a pre-audit result to the screenshot service unit 1032, the screenshot service unit 1032 obtains the target video data in real time, and obtains video frame information from the video stream according to the pre-audit result, so as to output the video frame information to the audit service unit 1033, the audit service unit 1033 displays the video frame information to an auditor for audit, the auditor may also provide the audit result to the audit service unit 1033, the audit service unit 1033 makes a decision according to the fed-back audit result, for example, when the audit result is that the target video data relates to violation content, the live broadcast of the target video data is prohibited, when the audit result is that the target video data is suspected to be violation, the screenshot mode is adjusted (for example, the screenshot mode is adjusted from the keyframe screenshot mode to the non-keyframe screenshot mode), and the adjusted screenshot mode is fed back to the screenshot service unit 1032, so that the service unit 1032 can perform screenshot on the target video data according to the adjusted screenshot mode And continuously performing screenshot verification on the target video data.
The present disclosure is described below by way of examples.
Fig. 2 illustrates a flow chart of an information processing method according to an embodiment of the present disclosure. The method illustrated in FIG. 2 may be performed by the screenshot service element 1032 illustrated in FIG. 1. As shown in fig. 2, the information processing method includes the following steps S201 to S202:
in step S201, determining an interval between two key frames in the target video data;
in step S202, one of a key frame screenshot mode and a non-key frame screenshot mode is selected according to the interval to obtain video frame information in the target video data.
In this embodiment, the target video data may be a video stream that is being live on a live platform by a live user. When a live broadcast user carries out live broadcast on a live broadcast platform, the target video data needs to be checked according to the requirements of relevant departments, and in the checking process, video frame information needs to be obtained from the target video data, and whether the content in the target video data meets relevant regulations or not is determined according to the video frame information.
Therefore, the embodiment of the disclosure may obtain an interval between two key frames in the target video data, and adaptively select the key frame capture mode or the non-key frame capture mode according to the interval to obtain the video frame information in the target video data. The interval between two key frames may be the interval between two key frames before and after in the target video data, that is, the length of one GOP (group of pictures). As shown in fig. 3, a GOP may include a key frame I, which is a complete picture, and a plurality of non-key frames P and B, which record changes relative to the I frame, which cannot be decoded without the I frame. Therefore, when the key frame I is acquired from the target video data, it can be directly output, and if a P frame or a B frame is acquired, it is also necessary to decode the P frame or the B frame from the I frame acquired nearby.
If a GOP in the target video data is long, that is, if the interval between two previous key frames and two subsequent key frames is large, if the key frame screenshot is adopted, information of the middle non-key frame may be omitted, and if the non-key frame screenshot is adopted, the cost may be too high (because the decoding of the non-key frame depends on the key frame or other non-key frames, the decoding process consumes resources). In the embodiment of the present disclosure, an adaptive adjustment mode is adopted, and a screenshot mode is adaptively adjusted according to an interval between two previous key frames and a next key frame, for example, when the interval between two key frames is too long, a non-key-frame screenshot mode (to prevent too much missing information) may be adopted, and when the interval between two key frames is short, a key-frame screenshot mode may be adopted (the missing information is not too much, and there is no great influence on the video content review).
After the real-time plug flow of the target video data arrives, the interval between two key frames in the target video data is determined, and then whether the target screenshot mode is the key frame screenshot mode or the non-key frame screenshot mode is determined according to the interval. By the method, the key frame screenshot mode or the non-key frame screenshot mode can be adaptively selected according to the interval between the two key frames in the target video data to acquire the video frame information from the target video data, so that balance can be achieved in cost and benefit, and the video content in the target video data is not omitted to the greatest extent while the cost waste is avoided.
In an optional implementation manner of this embodiment, before the step S201 of determining the interval between two key frames in the target video data, the method further includes the following steps:
obtaining a pre-review result of the target video data; the pre-auditing result comprises a target screenshot mode of the target video data; the target screenshot mode includes one of a key frame screenshot mode, a non-key frame screenshot mode, and an adaptive screenshot mode.
In this optional implementation manner, before screenshot review is performed on the target video data, pre-review may also be performed on the target video data to be generated according to the requirement of the live broadcast platform and the historical behavior data of the live broadcast user, and the pre-review result may be output to the screenshot service unit 1032 that executes to acquire video frame information in the target video data. The screenshot service unit 1032 can also acquire live target video data from the platform server 102 in real time, and process the target video data according to a pre-review result to acquire video frame information therein.
The pre-review result is used to instruct the screenshot service unit 1032 to obtain a target screenshot mode of video frame information from the target video data. The inventor of the present disclosure finds that the prior art target capture modes generally include only a key frame capture mode and a non-key frame capture mode. In the non-key frame screenshot mode, as known to those skilled in the art, the intercepted non-key frame needs to be decoded by the reference frame during encoding, that is, the non-key frame needs to be decoded according to the key frame in front of the non-key frame and other non-key frames, which results in higher calculation consumption and higher cost. However, if the key frame screenshot mode is adopted, although the cost is low, since the content expressed by the key frame is not the whole content of the target video data, omission occurs, the final audit result given by the auditor may not be hundreds of accurate, the target video data which may cause violation is also live broadcast by the live broadcast platform, and finally the operation of the live broadcast platform may be endangered.
Therefore, in the information processing method provided by the embodiment of the present disclosure, the pre-review result at least may include a target screenshot mode of the target video data; the target screenshot mode is a key frame screenshot mode, a non-key frame screenshot mode or a self-adaptive adjustment mode; that is, the embodiments of the present disclosure may also employ an adaptive adjustment mode in case of limited cost.
In an optional implementation manner of this embodiment, the step S201, that is, the step of determining the interval between two key frames in the target video data, further includes the following steps:
and when the target screenshot mode is the self-adaptive adjustment mode, determining the interval between two key frames in the target video data.
In this optional implementation manner, when the pre-review result is in the adaptive adjustment mode, the embodiment of the present disclosure may first obtain an interval between two key frames in the target video data, and adaptively select the key frame capture mode or the non-key frame capture mode according to the interval to obtain the video frame information in the target video data.
In an optional implementation manner of this embodiment, the pre-review result further includes a screenshot period.
In this alternative implementation, the capture period is a parameter indicating how long or how many image frames to capture one piece of image frame information for the target video data currently being live. During pre-auditing, the screenshot period can be determined according to actual conditions, for example, according to the requirements of a live broadcast platform, historical behavior data of a live broadcast user and the like, if the live broadcast platform requires to control the cost, the screenshot period can be set to be larger, otherwise, the live broadcast platform requires to accurately audit results, and the screenshot period can be set to be smaller; in addition, if the live broadcast user is historically checked out that the illegal video is played, the screenshot period can be set to be shorter aiming at the live broadcast video of the live broadcast user, and the live broadcast video of the live broadcast user can be strictly checked as far as possible. The screenshot period may be determined according to an actual situation, and is not limited herein.
In an optional implementation manner of this embodiment, the step S202, namely, the step of obtaining the video frame information in the target video data by selecting one of the key frame screenshot mode and the non-key frame screenshot mode according to the interval, further includes at least one of the following steps:
when the interval is less than or equal to the screenshot period, acquiring the video frame information in the target video data by adopting a key frame screenshot mode;
and when the interval is larger than the screenshot period, acquiring the video frame information in the target video data by adopting a non-key frame screenshot mode.
In this optional implementation manner, in the adaptive adjustment mode, whether the key frame screenshot mode or the non-key frame screenshot mode is selected may be determined by comparing the interval between two key frames with a preset threshold. The preset threshold may be a screenshot period in the pre-review result, or may be a numerical value determined in other manners. Under the condition that the preset threshold is set as the screenshot period, when the interval between two key frames is smaller than or equal to the screenshot period, and the target video data is screenshot according to the requirements of the screenshot period in the pre-review result, the first frame which is normally intercepted is the key frame, and the screenshot is performed again through one screenshot period, so that the intercepted key frame is either the next key frame (under the condition that the screenshot period is equal to the interval) or the non-key frame in the next group of GOPs, and therefore, the video content obtained by directly adopting the key frame screenshot mode under the condition is more accurate. For example, currently, the key frame a1 in the first group GOP is intercepted after the screenshot period, and the non-key frame B1 in the second group GOP is intercepted, and the decoding of the non-key frame B1 actually depends on the key frame a2 in the second group GOP (in some cases, it may also depend on other non-key frames before B1, only the dependent key frame is taken as an example), but since the key frame a2 and other non-key frames in the second group GOP are not intercepted according to the screenshot period and the non-key frame screenshot mode, the decoding of the non-key frame B1 can only use the most recently intercepted key frame, that is, the key frame a1, but the decoded video content depends on the key frame content of the first group GOP, and the video content may have a certain error from the actual content, in this case, if the key frame screenshot mode is adopted, the key frame a1 is intercepted for the first time, the key frame a2 is intercepted for the second time, it can be appreciated that the video content resulting from decoding non-key frames B1 by relying on key frame a1 is clearly less accurate than the video content of key frame a 2. Therefore, when the interval between the two key frames is less than or equal to the screenshot period, the requirement of the screenshot period is met (the actual screenshot period is equal to or less than the screenshot period in the pre-check result), the cost can be saved, and the video content obtained by screenshot is more accurate and complete. And when the interval between the two key frames is larger than the screenshot period, when the target video data is screenshot according to the requirements of the screenshot period in the pre-review result, the first frame intercepted is usually the key frame in the target video data, and the screenshot is performed again after one screenshot period, so that the non-key frame in the same group of GOP as the first frame is intercepted, and the method is suitable for the non-key frame screenshot mode under the condition that the content in the target video information is not omitted.
In some embodiments, when the interval between the two previous and next key frames in the adaptive adjustment mode is determined as the key frame screenshot mode, the screenshot period in the pre-review screenshot mode may be continuously used, and when the interval is not the key frame screenshot mode, the screenshot period may be adjusted to be screenshot for each frame so as not to omit the video content. It can be understood that, when the key frame screenshot mode is determined, the length of the GOP may be used as the screenshot period, that is, only the key frame is intercepted (if the GOP of the target video data is not changed), and when the key frame screenshot mode is determined to be the non-key frame screenshot mode, the screenshot period in the pre-review screenshot mode may also be continuously used for screenshot (meeting the pre-review requirement).
In an optional implementation manner of this embodiment, the step S201, that is, the step of determining the interval between two key frames in the target video data, further includes the following steps:
and acquiring video frame information in the target video data by adopting a non-key frame screenshot mode, and determining the interval according to the video frame information.
In the optional implementation manner, because the interval between the front key frame and the back key frame in the target video data is unknown under the initial condition, in the adaptive adjustment mode, at the initial stage of arrival of the target video data, the non-key frame screenshot mode is firstly adopted to screenshot the target video data, each frame in the target video data is intercepted, after the screenshot process of one GOP or a plurality of GOPs, the interval between the front key frame and the back key frame can be determined, and then the key frame screenshot mode or the non-key frame screenshot mode is determined to be adopted at the end according to the interval.
In an optional implementation manner of this embodiment, the method further includes at least one of the following steps:
when the target screenshot mode is a key frame screenshot mode, intercepting key frame information from the target video data acquired in real time according to the screenshot period;
and when the target screenshot mode is a non-key frame screenshot mode, video frame information including non-key frame information is intercepted from the target video data acquired in real time according to the screenshot period.
In the optional implementation mode, when the pre-review result is that the target screenshot mode is the key frame screenshot mode, directly adopting the screenshot period in the pre-review result to screenshot the target video data to obtain key frame information; in the case that the screenshot period is not consistent with the GOP, if non-key frame information is intercepted, the latest key frame information is used for replacement. And when the pre-check result is that the target screenshot mode is a non-key frame screenshot mode, adopting a screenshot period in the pre-check result to screenshot the target video data to obtain video frame information, wherein the video frame information comprises non-key frame information, and in some cases, the video frame information also comprises key frame information. In the non-key frame screenshot mode, if the intercepted key frame is the key frame, the intercepted key frame is directly output, and if the intercepted key frame is the non-key frame, the non-key frame is output after being decoded by using the previously intercepted key frame and/or the decoded non-key frame information.
It can be understood that the processing procedures of the non-key frame screenshot mode and the key frame screenshot mode determined in the adaptive screenshot mode are the same as those described above, and the actual screenshot period may be determined according to the screenshot period in the pre-review result or according to the screenshot period re-determined in the adaptive mode, which may be determined according to the actual situation, and is not described herein again.
In an optional implementation manner of this embodiment, the method further includes the following steps:
and auditing the target video data according to the video frame information to determine whether illegal contents exist in the target video data.
In this embodiment, after the screenshot service unit 1032 shown in fig. 1 acquires video frame information from the target video data according to the method for acquiring video frame information disclosed in the foregoing embodiment, the video frame information is output to the auditing service unit 1033 shown in fig. 1, and the auditing service unit 1033 may audit the target video data according to the received video frame information.
After receiving the video frame information, the auditing service unit 1033 may audit the video frame information by using a preset auditing rule, for example, the video frame information may be identified by a pre-trained neural network model, and an auditor may also perform an assisted auditing to finally obtain an auditing result.
In an optional implementation manner of this embodiment, the method further includes the following steps:
and adjusting a target video screenshot mode of the target video data according to the auditing result of the target video data.
In this optional implementation, the determined target capture mode may be updated and adjusted in the capture process of the target video data. In the auditing process of the target video data, after a period of screenshot in the early period and the auditing of the intercepted video frame information, when the current target video data is determined to be suitable for adopting a target screenshot mode different from the current used mode, the current target screenshot mode can be adjusted. For example, after a period of time of auditing, it is found that target video data may relate to some illegal contents, but because a key frame screenshot mode is currently adopted, or a screenshot period is long when a non-key frame screenshot mode is adopted, the obtained video frame information is not complete contents and cannot be determined in percentage, the target screenshot mode can be updated to the non-key frame screenshot mode, and all video frame information in the target video data is obtained in a manner that each frame is intercepted, so that the auditing server can audit the target video data again.
The following are embodiments of the disclosed apparatus that may be used to perform embodiments of the disclosed methods.
Fig. 4 shows a block diagram of the structure of an information processing apparatus according to an embodiment of the present disclosure. The apparatus shown in fig. 4 may be located in the screenshot service unit 1032 shown in fig. 1. As shown in fig. 4, the information processing apparatus includes:
a first determining module 401 configured to determine an interval between two key frames in the target video data;
a first obtaining module 402, configured to obtain video frame information in the target video data according to the interval in one of a key frame screenshot mode and a non-key frame screenshot mode.
In this embodiment, the target video data may be a video stream that is being live on a live platform by a live user. When a live broadcast user carries out live broadcast on a live broadcast platform, the target video data needs to be checked according to the requirements of relevant departments, and in the checking process, video frame information needs to be obtained from the target video data, and whether the content in the target video data meets relevant regulations or not is determined according to the video frame information.
Therefore, the embodiment of the disclosure may obtain an interval between two key frames in the target video data, and adaptively select the key frame capture mode or the non-key frame capture mode according to the interval to obtain the video frame information in the target video data. The interval between two key frames may be the interval between two key frames before and after in the target video data, that is, the length of one GOP (group of pictures). As shown in fig. 3, a GOP may include a key frame I, which is a complete picture, and a plurality of non-key frames P and B, which record changes relative to the I frame, which cannot be decoded without the I frame.
Therefore, when the key frame I is acquired from the target video data, it can be directly output, and if a P frame or a B frame is acquired, it is also necessary to decode the P frame or the B frame from the I frame acquired nearby.
If a GOP in the target video data is long, that is, if the interval between two previous key frames and two subsequent key frames is large, if the key frame screenshot is adopted, information of the middle non-key frame may be omitted, and if the non-key frame screenshot is adopted, the cost may be too high (because the decoding of the non-key frame depends on the key frame or other non-key frames, the decoding process consumes resources). In the embodiment of the present disclosure, an adaptive adjustment mode is adopted, and a screenshot mode is adaptively adjusted according to an interval between two previous key frames and a next key frame, for example, when the interval between two key frames is too long, a non-key-frame screenshot mode (to prevent too much missing information) may be adopted, and when the interval between two key frames is short, a key-frame screenshot mode may be adopted (the missing information is not too much, and there is no great influence on the video content review).
According to the embodiment of the disclosure, after the real-time plug flow of the target video data comes, the interval between two key frames in the target video data is determined, and then whether the target screenshot mode is the key frame screenshot mode or the non-key frame screenshot mode is determined according to the interval. By the method, the key frame screenshot mode or the non-key frame screenshot mode can be adaptively selected according to the interval between the two key frames in the target video data to acquire the video frame information from the target video data, so that balance can be achieved in cost and benefit, and the video content in the target video data is not omitted to the greatest extent while the cost waste is avoided.
In an optional implementation manner of this embodiment, before the first determining module 401, the apparatus further includes:
the second acquisition module is configured to acquire a pre-review result of the target video data; the pre-auditing result comprises a target screenshot mode of the target video data; the target screenshot mode includes one of a key frame screenshot mode, a non-key frame screenshot mode, and an adaptive screenshot mode.
In this optional implementation manner, before screenshot review is performed on the target video data, pre-review may also be performed on the target video data to be generated according to the requirement of the live broadcast platform and the historical behavior data of the live broadcast user, and the pre-review result may be output to the screenshot service unit 1032 that executes to acquire video frame information in the target video data. The screenshot service unit 1032 can also acquire live target video data from the platform server 102 in real time, and process the target video data according to a pre-review result to acquire video frame information therein.
The pre-review result is used to instruct the screenshot service unit 1032 to obtain a target screenshot mode of video frame information from the target video data. The inventor of the present disclosure finds that the prior art target capture modes generally include only a key frame capture mode and a non-key frame capture mode. In the non-key frame screenshot mode, as known to those skilled in the art, the intercepted non-key frame needs to be decoded by the reference frame during encoding, that is, the non-key frame needs to be decoded according to the key frame in front of the non-key frame and other non-key frames, which results in higher calculation consumption and higher cost. However, if the key frame screenshot mode is adopted, although the cost is low, since the content expressed by the key frame is not the whole content of the target video data, omission occurs, the final audit result given by the auditor may not be hundreds of accurate, the target video data which may cause violation is also live broadcast by the live broadcast platform, and finally the operation of the live broadcast platform may be endangered.
Therefore, in the method for acquiring video frame information provided by the embodiment of the present disclosure, the pre-review result at least may include a target screenshot mode of the target video data; the target screenshot mode is a key frame screenshot mode, a non-key frame screenshot mode or a self-adaptive adjustment mode; that is, the embodiments of the present disclosure may also employ an adaptive adjustment mode in case of limited cost.
In an optional implementation manner of this embodiment, the first determining module 401 further includes:
and the determining sub-module is configured to determine the interval between two key frames in the target video data when the target screenshot mode is the adaptive adjustment mode.
In this optional implementation manner, when the pre-review result is in the adaptive adjustment mode, the embodiment of the present disclosure may first obtain an interval between two key frames in the target video data, and adaptively select the key frame capture mode or the non-key frame capture mode according to the interval to obtain the video frame information in the target video data.
In an optional implementation manner of this embodiment, the pre-review result further includes a screenshot period.
In this alternative implementation, the capture period is a parameter indicating how long or how many image frames to capture one piece of image frame information for the target video data currently being live. During pre-auditing, the screenshot period can be determined according to actual conditions, for example, according to the requirements of a live broadcast platform, historical behavior data of a live broadcast user and the like, if the live broadcast platform requires to control the cost, the screenshot period can be set to be larger, otherwise, the live broadcast platform requires to accurately audit results, and the screenshot period can be set to be smaller; in addition, if the live broadcast user is historically checked out that the illegal video is played, the screenshot period can be set to be shorter aiming at the live broadcast video of the live broadcast user, and the live broadcast video of the live broadcast user can be strictly checked as far as possible. The screenshot period may be determined according to an actual situation, and is not limited herein.
In an optional implementation manner of this embodiment, the first obtaining module 402 further includes at least one of:
a first obtaining sub-module configured to obtain the video frame information in the target video data in a key frame screenshot mode when the interval is less than or equal to the screenshot period;
and the second obtaining submodule is configured to obtain the video frame information in the target video data in a non-key frame screenshot mode when the interval is greater than the screenshot period.
In this optional implementation manner, in the adaptive adjustment mode, whether the key frame screenshot mode or the non-key frame screenshot mode is selected may be determined by comparing the interval between two key frames with a preset threshold. The preset threshold may be a screenshot period in the pre-review result, or may be a numerical value determined in other manners. Under the condition that the preset threshold is set as the screenshot period, when the interval between two key frames is smaller than or equal to the screenshot period, and the target video data is screenshot according to the requirements of the screenshot period in the pre-review result, the first frame which is normally intercepted is the key frame, and the screenshot is performed again through one screenshot period, so that the intercepted key frame is either the next key frame (under the condition that the screenshot period is equal to the interval) or the non-key frame in the next group of GOPs, and therefore, the video content obtained by directly adopting the key frame screenshot mode under the condition is more accurate. For example, currently, the key frame a1 in the first group GOP is intercepted after the screenshot period, and the non-key frame B1 in the second group GOP is intercepted, and the decoding of the non-key frame B1 actually depends on the key frame a2 in the second group GOP (in some cases, it may also depend on other non-key frames before B1, only the dependent key frame is taken as an example), but since the key frame a2 and other non-key frames in the second group GOP are not intercepted according to the screenshot period and the non-key frame screenshot mode, the decoding of the non-key frame B1 can only use the most recently intercepted key frame, that is, the key frame a1, but the decoded video content depends on the key frame content of the first group GOP, and the video content may have a certain error from the actual content, in this case, if the key frame screenshot mode is adopted, the key frame a1 is intercepted for the first time, the key frame a2 is intercepted for the second time, it can be appreciated that the video content resulting from decoding non-key frames B1 by relying on key frame a1 is clearly less accurate than the video content of key frame a 2. Therefore, when the interval between the two key frames is less than or equal to the screenshot period, the requirement of the screenshot period is met (the actual screenshot period is equal to or less than the screenshot period in the pre-check result), the cost can be saved, and the video content obtained by screenshot is more accurate and complete. And when the interval between the two key frames is larger than the screenshot period, when the target video data is screenshot according to the requirements of the screenshot period in the pre-review result, the first frame intercepted is usually the key frame in the target video data, and the screenshot is performed again after one screenshot period, so that the non-key frame in the same group of GOP as the first frame is intercepted, and the method is suitable for the non-key frame screenshot mode under the condition that the content in the target video information is not omitted.
In some embodiments, when the interval between the two previous and next key frames in the adaptive adjustment mode is determined as the key frame screenshot mode, the screenshot period in the pre-review screenshot mode may be continuously used, and when the interval is not the key frame screenshot mode, the screenshot period may be adjusted to be screenshot for each frame so as not to omit the video content. It can be understood that, when the key frame screenshot mode is determined, the length of the GOP may be used as the screenshot period, that is, only the key frame is intercepted (if the GOP of the target video data is not changed), and when the key frame screenshot mode is determined to be the non-key frame screenshot mode, the screenshot period in the pre-review screenshot mode may also be continuously used for screenshot (meeting the pre-review requirement).
In an optional implementation manner of this embodiment, the first determining module 401 further includes:
and the third acquisition sub-module is configured to acquire video frame information in the target video data in a non-key frame screenshot mode and determine the interval according to the video frame information.
In the optional implementation manner, because the interval between the front key frame and the back key frame in the target video data is unknown under the initial condition, in the adaptive adjustment mode, at the initial stage of arrival of the target video data, the non-key frame screenshot mode is firstly adopted to screenshot the target video data, each frame in the target video data is intercepted, after the screenshot process of one GOP or a plurality of GOPs, the interval between the two key frames can be determined, and then the key frame screenshot mode or the non-key frame screenshot mode is determined to be adopted at the end according to the interval.
In an optional implementation manner of this embodiment, the apparatus further includes at least one of the following:
the first intercepting module is configured to intercept key frame information from the target video data acquired in real time according to the screenshot period when the target screenshot mode is a key frame screenshot mode;
and the second intercepting module is configured to intercept video frame information including non-key frame information from the target video data acquired in real time according to the screenshot period when the target screenshot mode is a non-key frame screenshot mode.
In the optional implementation mode, when the pre-review result is that the target screenshot mode is the key frame screenshot mode, directly adopting the screenshot period in the pre-review result to screenshot the target video data to obtain key frame information; in the case that the screenshot period is not consistent with the GOP, if non-key frame information is intercepted, the latest key frame information is used for replacement. And when the pre-check result is that the target screenshot mode is a non-key frame screenshot mode, adopting a screenshot period in the pre-check result to screenshot the target video data to obtain video frame information, wherein the video frame information comprises non-key frame information, and in some cases, the video frame information also comprises key frame information. In the non-key frame screenshot mode, if the intercepted key frame is the key frame, the intercepted key frame is directly output, and if the intercepted key frame is the non-key frame, the non-key frame is output after being decoded by using the previously intercepted key frame and/or the decoded non-key frame information.
It can be understood that the processing procedures of the non-key frame screenshot mode and the key frame screenshot mode determined in the adaptive screenshot mode are the same as those described above, and the actual screenshot period may be determined according to the screenshot period in the pre-review result or according to the screenshot period re-determined in the adaptive mode, which may be determined according to the actual situation, and is not described herein again.
In an optional implementation manner of this embodiment, the apparatus further includes:
and the auditing module is configured to audit the target video data according to the video frame information.
In this embodiment, the screenshot service unit 1032 shown in fig. 1 outputs the video frame information to the auditing service unit 1033 shown in fig. 1 after acquiring the video frame information from the target video data according to the video frame information acquisition device disclosed in the foregoing embodiment, and the auditing device of the video stream in the auditing service unit 1033 may audit the target video data according to the received video frame information to determine whether the target video data has illegal contents.
After receiving the video frame information, the auditing module may audit the video frame information by using a preset auditing rule, for example, the video frame information may be identified by a pre-trained neural network model, and an auditor may also perform an assisted auditing to finally obtain an auditing result.
In an optional implementation manner of this embodiment, the apparatus further includes:
and the adjusting module is configured to adjust a target video screenshot mode of the target video data according to the auditing result of the target video data.
In this optional implementation, the determined target capture mode may be updated and adjusted in the capture process of the target video data. In the auditing process of the target video data, after a period of screenshot in the early period and the auditing of the intercepted video frame information, when the current target video data is determined to be suitable for adopting a target screenshot mode different from the current used mode, the current target screenshot mode can be adjusted. For example, after a period of time of auditing, it is found that target video data may relate to some illegal contents, but because a key frame screenshot mode is currently adopted, or a screenshot period is long when a non-key frame screenshot mode is adopted, the obtained video frame information is not complete contents and cannot be determined in percentage, the target screenshot mode can be updated to the non-key frame screenshot mode, and all video frame information in the target video data is obtained in a manner that each frame is intercepted, so that the auditing server can audit the target video data again.
Fig. 5 is a schematic structural diagram of an electronic device suitable for implementing an information processing method according to an embodiment of the present disclosure.
As shown in fig. 5, the electronic apparatus 500 includes a Central Processing Unit (CPU)501 that can execute various processes in the embodiment shown in fig. 1 described above according to a program stored in a Read Only Memory (ROM)502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. In the RAM503, various programs and data necessary for the operation of the electronic apparatus 500 are also stored. The CPU501, ROM502, and RAM503 are connected to each other via a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
The following components are connected to the I/O interface 505: an input portion 506 including a keyboard, a mouse, and the like; an output portion 507 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 508 including a hard disk and the like; and a communication section 509 including a network interface card such as a LAN card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. The driver 510 is also connected to the I/O interface 505 as necessary. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as necessary, so that a computer program read out therefrom is mounted into the storage section 508 as necessary.
In particular, according to embodiments of the present disclosure, the method described above with reference to fig. 1 may be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program tangibly embodied on a medium readable thereby, the computer program including program code for performing a method for acquiring video frame information and auditing video streams in embodiments of the present disclosure. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 509, and/or installed from the removable medium 511.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowcharts or block diagrams may represent a module, a program segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units or modules described in the embodiments of the present disclosure may be implemented by software or hardware. The units or modules described may also be provided in a processor, and the names of the units or modules do not in some cases constitute a limitation of the units or modules themselves.
As another aspect, the present disclosure also provides a computer-readable storage medium, which may be the computer-readable storage medium included in the apparatus in the above-described embodiment; or it may be a separate computer readable storage medium not incorporated into the device. The computer readable storage medium stores one or more programs for use by one or more processors in performing the methods described in the present disclosure.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is possible without departing from the inventive concept. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.

Claims (18)

1. An information processing method characterized by comprising:
determining the interval between two key frames in the target video data;
selecting one of a key frame screenshot mode and a non-key frame screenshot mode according to the interval to obtain video frame information in the target video data;
the selecting one of a key frame screenshot mode and a non-key frame screenshot mode according to the interval to obtain the video frame information in the target video data comprises at least one of the following steps:
when the interval is less than or equal to a screenshot period, acquiring the video frame information in the target video data by adopting a key frame screenshot mode;
and when the interval is larger than the screenshot period, acquiring the video frame information in the target video data by adopting a non-key frame screenshot mode.
2. The method of claim 1, wherein prior to determining the interval between two key frames in the target video data, further comprising:
obtaining a pre-review result of the target video data; the pre-auditing result comprises a target screenshot mode of the target video data; the target screenshot mode includes one of a key frame screenshot mode, a non-key frame screenshot mode, and an adaptive screenshot mode.
3. The method of claim 2, wherein determining the interval between two key frames in the target video data comprises:
and when the target screenshot mode is the self-adaptive adjustment mode, determining the interval between two key frames in the target video data.
4. The method of claim 2, wherein the pre-audit result further comprises a screenshot period.
5. The method of any of claims 1-4, wherein determining the interval between two key frames in the target video data comprises:
and acquiring video frame information in the target video data by adopting a non-key frame screenshot mode, and determining the interval according to the video frame information.
6. The method according to any of claims 2-4, further comprising at least one of:
when the target screenshot mode is a key frame screenshot mode, intercepting key frame information from the target video data acquired in real time according to the screenshot period;
and when the target screenshot mode is a non-key frame screenshot mode, intercepting non-key frame information from the target video data acquired in real time according to the screenshot period.
7. The method according to any one of claims 1-4, further comprising: and auditing the target video data according to the video frame information.
8. The method of claim 7, further comprising:
and adjusting the target screenshot mode of the target video data according to the auditing result of the target video data.
9. An information processing apparatus characterized by comprising:
a first determining module configured to determine an interval between two key frames in target video data;
a first obtaining module configured to select one of a key frame screenshot mode and a non-key frame screenshot mode according to the interval to obtain video frame information in the target video data;
the selecting one of a key frame screenshot mode and a non-key frame screenshot mode according to the interval to obtain the video frame information in the target video data comprises at least one of the following steps:
when the interval is less than or equal to a screenshot period, acquiring the video frame information in the target video data by adopting a key frame screenshot mode;
and when the interval is larger than the screenshot period, acquiring the video frame information in the target video data by adopting a non-key frame screenshot mode.
10. The apparatus of claim 9, wherein the first determining module further comprises, prior to:
the second acquisition module is configured to acquire a pre-review result of the target video data; the pre-auditing result comprises a target screenshot mode of the target video data; the target screenshot mode includes one of a key frame screenshot mode, a non-key frame screenshot mode, and an adaptive screenshot mode.
11. The apparatus of claim 10, wherein the first determining module comprises:
and the determining sub-module is configured to determine the interval between two key frames in the target video data when the target screenshot mode is the adaptive adjustment mode.
12. The apparatus of claim 10, wherein the pre-audit result further comprises a screenshot period.
13. The apparatus of any of claims 9-12, wherein the first determining module comprises:
and the third acquisition sub-module is configured to acquire video frame information in the target video data in a non-key frame screenshot mode and determine the interval according to the video frame information.
14. The apparatus of any of claims 10-12, further comprising at least one of:
the first intercepting module is configured to intercept key frame information from the target video data acquired in real time according to the screenshot period when the target screenshot mode is a key frame screenshot mode;
and the second intercepting module is configured to intercept non-key frame information from the target video data acquired in real time according to the screenshot period when the target screenshot mode is a non-key frame screenshot mode.
15. The apparatus according to any one of claims 9-12, further comprising:
and the auditing module is configured to audit the target video data according to the video frame information.
16. The apparatus of claim 15, further comprising:
and the adjusting module is configured to adjust the target screenshot mode of the target video data according to the auditing result of the target video data.
17. An electronic device comprising a memory and a processor; wherein,
the memory is to store one or more computer instructions, wherein the one or more computer instructions are to be executed by the processor to implement the method of any one of claims 1-8.
18. A computer-readable storage medium having computer instructions stored thereon, wherein the computer instructions, when executed by a processor, implement the method of any one of claims 1-8.
CN201910153264.3A 2019-02-28 2019-02-28 Information processing method, information processing device, electronic equipment and computer readable storage medium Active CN111629261B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910153264.3A CN111629261B (en) 2019-02-28 2019-02-28 Information processing method, information processing device, electronic equipment and computer readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910153264.3A CN111629261B (en) 2019-02-28 2019-02-28 Information processing method, information processing device, electronic equipment and computer readable storage medium

Publications (2)

Publication Number Publication Date
CN111629261A CN111629261A (en) 2020-09-04
CN111629261B true CN111629261B (en) 2022-04-22

Family

ID=72273160

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910153264.3A Active CN111629261B (en) 2019-02-28 2019-02-28 Information processing method, information processing device, electronic equipment and computer readable storage medium

Country Status (1)

Country Link
CN (1) CN111629261B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101827264A (en) * 2009-03-06 2010-09-08 刘永 Hierarchical self-adaptive video frame sampling method
CN104837031A (en) * 2015-04-08 2015-08-12 中国科学院信息工程研究所 Method for high-speed self-adaptive video keyframe extraction
CN106534886A (en) * 2015-09-09 2017-03-22 无锡天脉聚源传媒科技有限公司 Method and device for indexing program
CN107707917A (en) * 2017-08-09 2018-02-16 南京邮电大学 A kind of video adaptive sample rate establishing method based on comentropy
WO2018036481A1 (en) * 2016-08-23 2018-03-01 华为技术有限公司 Method, device, and system for detecting scene change frame
CN108810622A (en) * 2018-07-09 2018-11-13 腾讯科技（深圳）有限公司 Extracting method, device, computer-readable medium and the electronic equipment of video frame

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101827264A (en) * 2009-03-06 2010-09-08 刘永 Hierarchical self-adaptive video frame sampling method
CN104837031A (en) * 2015-04-08 2015-08-12 中国科学院信息工程研究所 Method for high-speed self-adaptive video keyframe extraction
CN106534886A (en) * 2015-09-09 2017-03-22 无锡天脉聚源传媒科技有限公司 Method and device for indexing program
WO2018036481A1 (en) * 2016-08-23 2018-03-01 华为技术有限公司 Method, device, and system for detecting scene change frame
CN107707917A (en) * 2017-08-09 2018-02-16 南京邮电大学 A kind of video adaptive sample rate establishing method based on comentropy
CN108810622A (en) * 2018-07-09 2018-11-13 腾讯科技（深圳）有限公司 Extracting method, device, computer-readable medium and the electronic equipment of video frame

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
基于内容的视频检索关键技术研究述评;张婷婷;《农业图书情报学刊》;20091205(第12期);全文 *
采用非线性块稀疏字典选择的视频总结;马明阳等;《西安交通大学学报》;20181219(第05期);全文 *

Also Published As

Publication number Publication date
CN111629261A (en) 2020-09-04

Similar Documents

Publication Publication Date Title
CN110971929B (en) Cloud game video processing method, electronic equipment and storage medium
CN111178523A (en) Behavior detection method and device, electronic equipment and storage medium
CN109495467B (en) Method and device for updating interception rule and computer readable storage medium
CA3089584C (en) Techniques for predicting perceptual video quality based on complementary perceptual quality models
US11700383B2 (en) Techniques for modeling temporal distortions when predicting perceptual video quality
CN110856016A (en) Video live broadcast monitoring method and device, electronic equipment and storage medium
US10264273B2 (en) Computed information for metadata extraction applied to transcoding
CN111629261B (en) Information processing method, information processing device, electronic equipment and computer readable storage medium
CN114584758A (en) City-level monitoring video quality assessment method and system
CN113722588A (en) Resource recommendation method and device and electronic equipment
CN107734278B (en) Video playback method and related device
CN111314652B (en) Video structured analysis processing method, device, equipment and storage medium thereof
CN113628192A (en) Image blur detection method, device, apparatus, storage medium, and program product
CN116886880B (en) Method, device, equipment and computer program product for adjusting surveillance video
CN115460189B (en) Processing equipment testing method and device, computer and storage medium
EP1394737A2 (en) Device for embedding and extracting data in inter-frames
CN113747189B (en) Display control method and device for live broadcast information, electronic equipment and computer medium
US20170332112A1 (en) Generating synthetic frame features for sentinel frame matching
CN118524090A (en) Media file processing method, preview method and related equipment
CN114615508A (en) Decoding time detection method, decoding method and related equipment
CN113724220A (en) Video processing method and device, electronic equipment and computer readable storage medium
CN117493426A (en) Data visualization processing method, system, electronic equipment and storage medium
CN114205577A (en) Video playing pause detection method and device
CN118283298A (en) Video transmission method, processing method, apparatus, device, medium, and program product
CN117793388A (en) Live broadcast risk control method and device

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