CN110012365A - Video key frame extracting method and device - Google Patents
Video key frame extracting method and device Download PDFInfo
- Publication number
- CN110012365A CN110012365A CN201910240689.8A CN201910240689A CN110012365A CN 110012365 A CN110012365 A CN 110012365A CN 201910240689 A CN201910240689 A CN 201910240689A CN 110012365 A CN110012365 A CN 110012365A
- Authority
- CN
- China
- Prior art keywords
- frame
- barrage
- described image
- video
- character string
- 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.)
- Pending
Links
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
- H04N21/47—End-user applications
- H04N21/488—Data services, e.g. news ticker
- H04N21/4884—Data services, e.g. news ticker for displaying subtitles
Abstract
This application discloses a kind of video key frame extracting method and devices, by obtaining the multiple images frame in video, are ranked up with the appearance sequence of multiple images frame in video to multiple images frame；It is barrage by the string token of displacement is generated in adjacent picture frame, calculates the barrage quantity of each picture frame；All picture frames that barrage quantity in each picture frame is greater than preset threshold are extracted, as key frame of video.Compared with prior art, the barrage quantity that the application passes through acquisition picture frame, and pass through the key frame of barrage number of extracted video, so that the process of selection is relatively objective, and due to without calculating its dependent variable, only need to by barrage quantity number select key frame, simplify selection process, to more convenient and easy in the selection mode of key frame, and then achieve the effect that quick and precisely to extract Video Key picture.
Description
Technical field
This application involves teaching equipment technical field more particularly to a kind of video key frame extracting methods and device.
Background technique
With the development of multimedia technology, people can select the video for needing to watch by various terminals.Currently, various
The video of various kinds provides platform can provide a large amount of contents available for viewing, downloading for user, however in a large amount of content, user
Other than being selected to watch which video according to some information usually obtained, just platform can only be provided by video and be provided
Video information, such as title, brief introduction, thus to whether paying close attention to or watching the video and make a choice.But this mode is still
Not intuitive enough, user often understands the information of video one by one without grace time.
To solve the above problems, in the prior art, usually by its in video distribution person or platform selecting video frame think compared with
Classical one or more pictures, the representative key frame as video.But key frame of video is being carried out using the prior art
Selection when, discovery is artificial since this method relies on to be chosen, and its people's subjectivity of different personnel is different, and picture selection is caused to be deposited
In otherness, and its operation is time-consuming and cumbersome, and human cost is high, and working efficiency is low, therefore this method is neither objective, is also not easy
It carries out.
Summary of the invention
The embodiment of the present application provides a kind of video key frame extracting method and device, solves key frame of video in the prior art
Selection it is neither objective and be not easy the problem of carrying out.
To solve the above problems, the embodiment of the present application provides a kind of video key frame extracting method, it is suitable for calculating equipment
Middle execution includes at least following steps:
Obtain the multiple images frame in video, the time of occurrence based on multiple described image frames in the video, to more
A described image frame is ranked up；
It is barrage by the string token of displacement is generated in adjacent described image frame, calculates each described image frame
Barrage quantity；
All described image frames that barrage quantity in each described image frame is greater than preset threshold are extracted, as Video Key
Frame.
Further, described by the string token for generating displacement in adjacent described image frame is barrage, is calculated every
The barrage quantity of one described image frame, comprising:
It, will be after the boundary position for determining each character string according to the spacing distance of character string each in described image frame
Boundary position described in adjacent described image frame generates the character string of displacement, is labeled as the barrage, calculates each figure
As the barrage quantity of frame.
Further, described by the string token for generating displacement in adjacent described image frame is barrage, is calculated every
The barrage quantity of one described image frame, comprising:
The character string of displacement will be generated in the direction indicated in adjacent described image frame, be labeled as the barrage, meter
Calculate the barrage quantity of each described image frame.
Further, barrage quantity is made greater than all described image frames of preset threshold in extracting each described image frame
Before key frame of video, further includes:
Will with each described image frame it is one-to-one each barrage quantity is descending is ranked up, selection comes N
The barrage quantity of position is as the preset threshold.
Further, the character string includes at least a character；
When the character string includes the more than one character, the interval of the adjacent character is less than preset interval.
Further, a kind of key frame of video extraction element is also provided, comprising:
Image sorting module, for obtaining the multiple images frame in video, based on multiple described image frames in the video
In time of occurrence, multiple described image frames are ranked up；
Barrage computing module, for being barrage, meter by the string token for generating displacement in adjacent described image frame
Calculate the barrage quantity of each described image frame；
Text region module, all described images for being greater than preset threshold for extracting barrage quantity in each described image frame
Frame, as key frame of video.
Further, the barrage computing module is specifically used for:
According to the spacing distance of the character string each in described image frame, the boundary position of each character string is determined；
The boundary position described in adjacent described image frame is generated to the character string of displacement, is labeled as the barrage, meter
Calculate the barrage quantity of each described image frame.
Further, the barrage computing module is specifically used for:
The character string of displacement will be generated in the direction indicated in adjacent described image frame, be labeled as the barrage, meter
Calculate the barrage quantity of each described image frame.
Further, further includes:
Threshold value chooses module, and being used for will be with the one-to-one each descending progress of barrage quantity of each described image frame
Sequence chooses the barrage quantity for coming N as the preset threshold.
Further, the character string includes at least a character；
When the character string includes the more than one character, the interval of the adjacent character is less than preset interval.
Implement the embodiment of the present application, has the following beneficial effects:
A kind of video key frame extracting method and device provided by the embodiments of the present application, by obtaining multiple figures in video
As frame, multiple images frame is ranked up with the appearance sequence of multiple images frame in video；It will be produced in adjacent picture frame
The string token of raw displacement is barrage, calculates the barrage quantity of each picture frame；Barrage quantity in each picture frame is extracted to be greater than
All picture frames of preset threshold, as key frame of video.Compared with prior art, the barrage that the application passes through acquisition picture frame
Quantity, and pass through the key frame of barrage number of extracted video, so that the process of selection is relatively objective, and due to without calculating other changes
Amount, only need to by barrage quantity number select key frame, selection process is simplified, thus in the selection mode of key frame
It is more convenient and easy, and then achieve the effect that quick and precisely to extract Video Key picture.
Detailed description of the invention
Fig. 1 is the flow diagram for the video key frame extracting method that one embodiment of the application provides；
Fig. 2 is the flow diagram for the video key frame extracting method that the further embodiment of the application provides；
Fig. 3 is the flow diagram for the video key frame extracting method that another embodiment of the application provides；
Fig. 4 is the flow diagram for the video key frame extracting method that another embodiment of the application provides；
Fig. 5 is the structural schematic diagram for the key frame of video extraction element that one embodiment of the application provides；
Fig. 6 is the structural schematic diagram for the key frame of video extraction element that another embodiment of the application provides.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of embodiments of the present application, instead of all the embodiments.It is based on
Embodiment in the application, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall in the protection scope of this application.
Referring to Figure 1.
Referring to Fig. 1, it is the flow diagram of the video key frame extracting method of one embodiment offer of the application, such as schemes
Shown in 1, each step is specific as follows:
Step S10 obtains the multiple images frame in video, the time of occurrence based on multiple images frame in video, to more
A picture frame is ranked up.
In the present embodiment, the complete video containing barrage is obtained from each website or platform, to be taken out by preset duration
The form of frame, such as 0.5 second/frame, the appearance after obtaining the multiple images frame in any video, based on multiple images frame in video
Time is ranked up multiple images frame, and as unit of video name, sorts out to the multiple images frame after sequence, establishes view
Frequency image frame data library.
Step S12 is barrage by the string token of displacement is generated in adjacent picture frame, calculates each picture frame
Barrage quantity.
In the present embodiment, the identification of character string is based on optical character recognition technology.Due to passing through optical character identification skill
The character string that art recognizes may be video caption or background subtitle, therefore pass through the comparison of front and back picture frame, judge all look into
Whether the character string found generates displacement.It is barrage by the string token if the character string found generates displacement；It is no
Then, it is marked as video caption or background subtitle, to calculate the barrage quantity of each picture frame after realizing that barrage is chosen.
It should be noted that character string includes at least a character.It is adjacent when character string includes more than one character
The interval of character is less than preset interval.
Step S14 extracts all picture frames that barrage quantity in each picture frame is greater than preset threshold, as Video Key
Frame.
By barrage quantity come the key frame of selecting video, so that the process of selection is relatively objective, and due to without calculating it
Dependent variable, only need to by barrage quantity number select key frame, selection process is simplified, thus in the selection side of key frame
It is more convenient and easy in formula, and then achieve the effect that quick and precisely to extract Video Key picture.
Refer to Fig. 2.
Further, referring to fig. 2, be the application further embodiment provide video key frame extracting method process
Schematic diagram.Include:
Step S20 obtains the multiple images frame in video, when based on appearance of multiple described image frames in the video
Between, multiple described image frames are ranked up.
In the present embodiment, the implementation procedure of step S20 is similar with the implementation procedure of step S10 shown in FIG. 1, herein not
It repeats again.
Step S22, will be after the boundary position for determining each character string according to the spacing distance of character string each in picture frame
Boundary position generates the character string of displacement in adjacent picture frame, is labeled as barrage, calculates the barrage quantity of each picture frame.
It is made of due to character string at least one complete character, in the present embodiment, by judging image
Whether the distance between two characters adjacent in horizontal direction are greater than pre-determined distance in frame, to judge whether to belong to same word
Symbol string.Specifically, then two adjacent characters are divided into together when the distance between two adjacent characters are less than pre-determined distance
One character string；Otherwise, it is divided into kinds of characters string.According to division result, using the beginning and end position of character string as boundary
Behind position, by the character string that start or end position is subjected to displacement in adjacent picture frame, it is labeled as barrage, and complete institute
After having the label of barrage, the barrage quantity of each picture frame is calculated.
It should be noted that if then the position of beginning and end can be, but not limited to using the left side of character string as beginning
The initial character and end character of character string, or with boundary position tangent on the left of initial character and with it is tangent on the right side of end character
Boundary position.Similarly, it can be seen that details are not described herein using the right side of character string as the boundary position identification method of beginning.
Step S24 extracts all picture frames that barrage quantity in each picture frame is greater than preset threshold, as Video Key
Frame.
In the present embodiment, the implementation procedure of step S24 is similar with the implementation procedure of step S14 shown in FIG. 1, herein not
It repeats again.
Please refer to Fig. 3.
It is the flow diagram of the video key frame extracting method of another embodiment offer of the application, packet referring to Fig. 3
It includes:
Step S30 obtains the multiple images frame in video, when based on appearance of multiple described image frames in the video
Between, multiple described image frames are ranked up.
In the present embodiment, the implementation procedure of step S30 is similar with the implementation procedure of step S10 shown in FIG. 1, herein not
It repeats again.
Step S32 will generate in the direction indicated the character string of displacement in adjacent picture frame, be labeled as barrage, meter
Calculate the barrage quantity of each picture frame.
As a preferable examples of the present embodiment, assigned direction is to left dislocation.When knowing in the picture frame in former frame
The string token when relative displacement has occurred to the left in the picture frame of adjacent a later frame, is by the character string being clipped to
Barrage.When assigned direction is displacement to the right similarly.
As another preferable examples of the present embodiment, assigned direction is to left dislocation.When in the picture frame in former frame
The boundary position of the character string recognized will be with when relative displacement has occurred to the left in the picture frame of adjacent a later frame
The corresponding string token of the boundary position is barrage.When assigned direction is displacement to the right similarly.
Since the background subtitle of video is also possible to the case where being subjected to displacement in adjacent picture frame, such as music video
Background subtitle, therefore by being barrage by the string token being subjected to displacement in the direction indicated, it is ensured that carrying out barrage label
When, wrong target situation will not be generated, and then ensure the accuracy of barrage label.
Step S34 extracts all picture frames that barrage quantity in each picture frame is greater than preset threshold, as Video Key
Frame.
In the present embodiment, the implementation procedure of step S34 is similar with the implementation procedure of step S14 shown in FIG. 1, herein not
It repeats again.
Please refer to Fig. 4.
Referring to fig. 4, be the application another embodiment provide video key frame extracting method flow diagram, remove
Outside structure shown in Fig. 1, further includes:
Step S13, will each barrage quantity is descending correspondingly is ranked up with each picture frame, selection comes N
The barrage quantity of position is as preset threshold.
Wherein, N is positive integer.
In the present embodiment, right from more to few sequence with barrage quantity after the barrage quantity by calculating each picture frame
After barrage quantity is ranked up, mode of the barrage quantity for coming N as preset threshold is extracted, so that preset threshold is in
One self-adjustable state is extracted less than key frame when threshold value is excessively high to reduce, or works as the too low key frame extraction of threshold value
The situation of inaccuracy.
Please refer to Fig. 5.
It is the structural schematic diagram of the key frame of video extraction element of one embodiment offer of the application referring to Fig. 5.Packet
It includes:
Image sorting module 100, for obtaining the multiple images frame in video, based on multiple images frame going out in video
Between current, multiple images frame is ranked up.
In the present embodiment, image sorting module 100 is used for, and obtains the complete view containing barrage from each website or platform
Frequently, in the form of carrying out taking out frame by preset duration, such as 0.5 second/frame, after obtaining the multiple images frame in any video, based on more
The time of occurrence of a picture frame in video, is ranked up multiple images frame, and as unit of video name, after sequence
Multiple images frame is sorted out, and video image frame data library is established.
Barrage computing module 102 is calculated for being barrage by the string token for generating displacement in adjacent picture frame
The barrage quantity of each picture frame.
In the present embodiment, the identification of character string is based on optical character recognition technology.Due to passing through optical character identification skill
The character string that art recognizes may be video caption or background subtitle, therefore barrage computing module 102, for passing through front and back image
The comparison of frame, judges whether all character strings found generate displacement.If the character string found generates displacement, by the word
Symbol string is labeled as barrage；Otherwise, it is marked as video caption or background subtitle, to calculate each figure after realizing that barrage is chosen
As the barrage quantity of frame.
It should be noted that character string includes at least a character.It is adjacent when character string includes more than one character
The interval of character is less than preset interval.
As a preferable examples of the present embodiment, barrage computing module 102 is used for, according to character string each in picture frame
Spacing distance, after the boundary position for determining each character string, by adjacent picture frame boundary position generate the character string of displacement,
Labeled as barrage, the barrage quantity of each picture frame is calculated.
It is made of due to character string at least one complete character, in the present embodiment, by judging image
Whether the distance between two characters adjacent in horizontal direction are greater than pre-determined distance in frame, to judge whether to belong to same word
Symbol string.Specifically, then two adjacent characters are divided into together when the distance between two adjacent characters are less than pre-determined distance
One character string；Otherwise, it is divided into kinds of characters string.According to division result, using the beginning and end position of character string as boundary
Behind position, by the character string that start or end position is subjected to displacement in adjacent picture frame, it is labeled as barrage, and complete institute
After having the label of barrage, the barrage quantity of each picture frame is calculated.
It should be noted that if then the position of beginning and end can be, but not limited to using the left side of character string as beginning
The initial character and end character of character string, or with boundary position tangent on the left of initial character and with it is tangent on the right side of end character
Boundary position.Similarly, it can be seen that details are not described herein using the right side of character string as the boundary position identification method of beginning.
As another preferable examples of the present embodiment, barrage computing module 102 is used for, by adjacent picture frame
The character string of displacement is generated on assigned direction, is labeled as barrage, is calculated the barrage quantity of each picture frame.
Specifically, if assigned direction be to when left dislocation, when the character string recognized in the picture frame in former frame,
It is barrage by the string token when relative displacement has occurred in the picture frame of adjacent a later frame to the left.Assigned direction is
When being displaced to the right similarly.
Or, if assigned direction is to when left dislocation, when the boundary of the character string recognized in the picture frame in former frame
It position will character corresponding with the boundary position when relative displacement has occurred to the left in the picture frame of adjacent a later frame
String is labeled as barrage.When assigned direction is displacement to the right similarly.
Since the background subtitle of video is also possible to the case where being subjected to displacement in adjacent picture frame, such as music video
Background subtitle, therefore by being barrage by the string token being subjected to displacement in the direction indicated, it is ensured that carrying out barrage label
When, wrong target situation will not be generated, and then ensure the accuracy of barrage label.
Text region module 104, all picture frames for being greater than preset threshold for extracting barrage quantity in each picture frame, makees
For key frame of video.
By barrage quantity come the key frame of selecting video, so that the process of selection is relatively objective, and due to without calculating it
Dependent variable, only need to by barrage quantity number select key frame, selection process is simplified, thus in the selection side of key frame
It is more convenient and easy in formula, and then achieve the effect that quick and precisely to extract Video Key picture.
Please refer to Fig. 6.
It is the structural schematic diagram of the key frame of video extraction element of another embodiment offer of the application referring to Fig. 6.It removes
Outside structure shown in Fig. 5, further includes:
Threshold value chooses module 103, for will each barrage quantity is descending correspondingly is ranked up with each picture frame,
The barrage quantity for coming N is chosen as preset threshold.
In the present embodiment, right from more to few sequence with barrage quantity after the barrage quantity by calculating each picture frame
After barrage quantity is ranked up, mode of the barrage quantity for coming N as preset threshold is extracted, so that preset threshold is in
One self-adjustable state is extracted less than key frame when threshold value is excessively high to reduce, or works as the too low key frame extraction of threshold value
The situation of inaccuracy.
The embodiment of the present application provides a kind of video key frame extracting method and device, passes through the multiple images obtained in video
Frame is ranked up multiple images frame with the appearance sequence of multiple images frame in video；It will be generated in adjacent picture frame
The string token of displacement is barrage, calculates the barrage quantity of each picture frame；Barrage quantity in each picture frame is extracted to be greater than in advance
If all picture frames of threshold value, as key frame of video.Compared with prior art, the barrage number that the application passes through acquisition picture frame
Amount, and pass through the key frame of barrage number of extracted video, so that the process of selection is relatively objective, and due to without calculating other changes
Amount, only need to by barrage quantity number select key frame, selection process is simplified, thus in the selection mode of key frame
It is more convenient and easy, and then achieve the effect that quick and precisely to extract Video Key picture.
The another embodiment of the application additionally provides a kind of key frame of video extraction terminal device, including processor, storage
Device and storage in the memory and are configured as the computer program executed by the processor, and the processor executes
The video key frame extracting method as described in above-described embodiment is realized when the computer program.
The above is the preferred embodiment of the application, it is noted that for those skilled in the art
For, under the premise of not departing from the application principle, several improvements and modifications can also be made, these improvements and modifications are also considered as
The protection scope of the application.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the program can be stored in a computer-readable storage medium
In, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, the storage medium can be magnetic
Dish, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random Access
Memory, RAM) etc..
Claims (10)
1. a kind of video key frame extracting method, which is characterized in that include at least following steps:
Obtain the multiple images frame in video, the time of occurrence based on multiple described image frames in the video, to multiple institutes
Picture frame is stated to be ranked up；
It is barrage by the string token of displacement is generated in adjacent described image frame, calculates the barrage of each described image frame
Quantity；
All described image frames that barrage quantity in each described image frame is greater than preset threshold are extracted, as key frame of video.
2. video key frame extracting method according to claim 1, which is characterized in that it is described will be in adjacent described image
The string token that displacement is generated in frame is barrage, calculates the barrage quantity of each described image frame, comprising:
It, will be adjacent after the boundary position for determining each character string according to the spacing distance of character string each in described image frame
Described image frame described in boundary position generate displacement character string, be labeled as the barrage, calculate each described image frame
Barrage quantity.
3. video key frame extracting method according to claim 1, which is characterized in that it is described will be in adjacent described image
The string token that displacement is generated in frame is barrage, calculates the barrage quantity of each described image frame, comprising:
The character string of displacement will be generated in the direction indicated in adjacent described image frame, be labeled as the barrage, calculate every
The barrage quantity of one described image frame.
4. video key frame extracting method according to claim 1, which is characterized in that be hit by a bullet extracting each described image frame
Curtain quantity is greater than all described image frames of preset threshold, before key frame of video, further includes:
Will with each described image frame it is one-to-one each barrage quantity is descending is ranked up, selection comes N
Barrage quantity is as the preset threshold.
5. video key frame extracting method according to any one of claims 1-4, which is characterized in that the character string is extremely
It less include a character；
When the character string includes the more than one character, the interval of the adjacent character is less than preset interval.
6. a kind of key frame of video extraction element characterized by comprising
Image sorting module, for obtaining the multiple images frame in video, based on multiple described image frames in the video
Time of occurrence is ranked up multiple described image frames；
Barrage computing module calculates every for being barrage by the string token for generating displacement in adjacent described image frame
The barrage quantity of one described image frame；
Text region module, all described image frames for being greater than preset threshold for extracting barrage quantity in each described image frame,
As key frame of video.
7. key frame of video extraction element according to claim 6, which is characterized in that the barrage computing module is specifically used
In:
According to the spacing distance of the character string each in described image frame, the boundary position of each character string is determined；
The boundary position described in adjacent described image frame is generated to the character string of displacement, is labeled as the barrage, is calculated every
The barrage quantity of one described image frame.
8. key frame of video extraction element according to claim 6, which is characterized in that the barrage computing module is specifically used
In:
The character string of displacement will be generated in the direction indicated in adjacent described image frame, be labeled as the barrage, calculate every
The barrage quantity of one described image frame.
9. key frame of video extraction element according to claim 6, which is characterized in that further include:
Threshold value chooses module, for will one-to-one each barrage quantity is descending arranges with each described image frame
Sequence chooses the barrage quantity for coming N as the preset threshold.
10. according to key frame of video extraction element described in claim 6-9 any one, which is characterized in that the character string
Including at least a character；
When the character string includes the more than one character, the interval of the adjacent character is less than preset interval.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910240689.8A CN110012365A (en) | 2019-03-27 | 2019-03-27 | Video key frame extracting method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910240689.8A CN110012365A (en) | 2019-03-27 | 2019-03-27 | Video key frame extracting method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110012365A true CN110012365A (en) | 2019-07-12 |
Family
ID=67168480
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910240689.8A Pending CN110012365A (en) | 2019-03-27 | 2019-03-27 | Video key frame extracting method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110012365A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110399847A (en) * | 2019-07-30 | 2019-11-01 | 北京字节跳动网络技术有限公司 | Extraction method of key frame, device and electronic equipment |
| CN111080754A (en) * | 2019-12-12 | 2020-04-28 | 广东智媒云图科技股份有限公司 | Character animation production method and device for connecting characteristic points of head and limbs |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104994425A (en) * | 2015-06-30 | 2015-10-21 | 北京奇艺世纪科技有限公司 | Video labeling method and device |
| US20160366466A1 (en) * | 2014-07-07 | 2016-12-15 | Le Holdings(Beijing)Co., Ltd. | Method for displaying bullet screen of video, and electronic device |
| CN106331877A (en) * | 2016-09-22 | 2017-01-11 | 广州华多网络科技有限公司 | Bullet screen playing method and device |
| CN106921867A (en) * | 2015-12-25 | 2017-07-04 | 北京奇虎科技有限公司 | A kind of video representativeness picture, fragment determine method and apparatus |
| CN109089154A (en) * | 2018-07-10 | 2018-12-25 | 武汉斗鱼网络科技有限公司 | A kind of video extraction method, apparatus, equipment and medium |
-
2019
- 2019-03-27 CN CN201910240689.8A patent/CN110012365A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160366466A1 (en) * | 2014-07-07 | 2016-12-15 | Le Holdings(Beijing)Co., Ltd. | Method for displaying bullet screen of video, and electronic device |
| CN104994425A (en) * | 2015-06-30 | 2015-10-21 | 北京奇艺世纪科技有限公司 | Video labeling method and device |
| CN106921867A (en) * | 2015-12-25 | 2017-07-04 | 北京奇虎科技有限公司 | A kind of video representativeness picture, fragment determine method and apparatus |
| CN106331877A (en) * | 2016-09-22 | 2017-01-11 | 广州华多网络科技有限公司 | Bullet screen playing method and device |
| CN109089154A (en) * | 2018-07-10 | 2018-12-25 | 武汉斗鱼网络科技有限公司 | A kind of video extraction method, apparatus, equipment and medium |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110399847A (en) * | 2019-07-30 | 2019-11-01 | 北京字节跳动网络技术有限公司 | Extraction method of key frame, device and electronic equipment |
| CN110399847B (en) * | 2019-07-30 | 2021-11-09 | 北京字节跳动网络技术有限公司 | Key frame extraction method and device and electronic equipment |
| CN111080754A (en) * | 2019-12-12 | 2020-04-28 | 广东智媒云图科技股份有限公司 | Character animation production method and device for connecting characteristic points of head and limbs |
| CN111080754B (en) * | 2019-12-12 | 2023-08-11 | 广东智媒云图科技股份有限公司 | Character animation production method and device for connecting characteristic points of head and limbs |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Smith et al. | Video skimming and characterization through the combination of image and language understanding | |
| CN110287949B (en) | Video clip extraction method, device, equipment and storage medium | |
| CN101553814B (en) | Method and apparatus for generating a summary of a video data stream | |
| US20110064381A1 (en) | Method and apparatus for identifying video transitions | |
| CN105744292A (en) | Video data processing method and device | |
| CN109766883B (en) | Method for rapidly extracting network video subtitles based on deep neural network | |
| US8391355B2 (en) | Method and device for online dynamic semantic video compression and video indexing | |
| Corridoni et al. | Structured representation and automatic indexing of movie information content | |
| WO2011125322A1 (en) | Apparatus and method for identifying a still image contained in moving image contents | |
| CN104217008A (en) | Interactive type labeling method and system for Internet figure video | |
| CN110012365A (en) | Video key frame extracting method and device | |
| KR100374040B1 (en) | Method for detecting caption synthetic key frame in video stream | |
| CN108989875A (en) | A kind of method and device generating barrage file | |
| CN111401238A (en) | Method and device for detecting character close-up segments in video | |
| CN109408672A (en) | A kind of article generation method, device, server and storage medium | |
| CN107239503A (en) | Video display method and device | |
| de Abreu et al. | Toward content-driven intelligent authoring of mulsemedia applications | |
| CN108153882A (en) | A kind of data processing method and device | |
| CN116308530A (en) | Advertisement implantation method, advertisement implantation device, advertisement implantation equipment and readable storage medium | |
| JP2006217046A (en) | Video index image generator and generation program | |
| Yang et al. | Key frame extraction using unsupervised clustering based on a statistical model | |
| CN110287376A (en) | A method of the important vidclip of extraction based on drama and caption analysis | |
| CN108985244A (en) | A kind of television program type recognition methods and device | |
| CN106899876A (en) | The methods of exhibiting and device of a kind of video feature information | |
| CN112381151B (en) | Method and device for determining similar videos |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190712 |
|
| RJ01 | Rejection of invention patent application after publication |