CN109788346A - Video file Command Line Parsing method - Google Patents
Video file Command Line Parsing method Download PDFInfo
- Publication number
- CN109788346A CN109788346A CN201810944771.4A CN201810944771A CN109788346A CN 109788346 A CN109788346 A CN 109788346A CN 201810944771 A CN201810944771 A CN 201810944771A CN 109788346 A CN109788346 A CN 109788346A
- Authority
- CN
- China
- Prior art keywords
- equipment
- pixel
- image
- file
- video
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Abstract
The present invention relates to a kind of video file Command Line Parsing methods, this method includes parsing video file using a kind of video file Command Line Parsing system, the video file Command Line Parsing system includes: scene display equipment, for showing red text corresponding with the plays for children identification signal when receiving the plays for children identification signal；Video storaging equipment, for video file data library to be stored in advance, the video file data library saves each video file folder, is placed with single target file and configuration file corresponding with the file destination including video content in each video file folder；File searches equipment, for according to the user's choice, obtain the video files names chosen by user, corresponding video file folder is found in video file data library based on the video files names, the file destination including video content is obtained from video file folder, and plays the file destination.
Description
Technical field
The present invention relates to video parsing field more particularly to a kind of video file Command Line Parsing methods.
Background technique
It the use of frequent video file format include audio video interleaved and QuickTime file format.
Audio video interleaved is a kind of digital audio for meeting RIFF filespec and video of Microsoft Corporation exploitation
File format is formerly used for Microsoft Video for Windows environment, by majorities such as Windows 95/98, OS/2
Operating system is directly supported.AVI format allows video and audio to be interleaved together and be played simultaneously, and supports 256 colors and RLE compression,
But avi file does not limit compression standard, and therefore, audio video interleaved is intended only as the standard in control interface, does not have compatibility
Property, with the avi file of different compression algorithms generation, it is necessary to can just be played back using corresponding decompression algorithm.Common AVI
Video 1 in broadcasting driver, mainly Microsoft Video for Windows or Windows 95/98, and
The Indeo Video of Intel Company.
QuickTime file format is a kind of audio of apple computer company exploitation, video file format, for protecting
Deposit audio and video information, have advanced video and audio-frequency function, be capable of providing to include Apple Mas OS,
The support of all mainstream operation system platforms including Microsoft Windows.QuickTime file format supports 25 coloured silks
Color supports the leading integrated compress techniques such as RLE, JPEG, provides 150 various video effects, and be furnished with and provide more than 200 kinds
The compatible sound equipment of MIDI and the sound of equipment are full-time.QuickTime contains the key characteristic based on Internet application, Neng Goutong
It crosses Internet and real-time digital information stream, workflow and file playback function is provided, in addition, QuickTime is additionally used
A kind of virtual reality technology being known as QuickTime VR technology, Interactive control of the user by mouse or keyboard, Ke Yiguan
Examine 360 degree around a certain place of scene, or the jobbie from any angle in space.QuickTime is leading with its
Multimedia technology and cross-platform characteristic, lesser memory space require, the high opening of the independence of technical detail and system
Property, obtain being widely recognized as industry.
Summary of the invention
In order to solve the technical problem of every Digital video resolution difficulty in the prior art, the present invention provides a kind of views
Frequency file Command Line Parsing method.
The present invention at least has the important inventive point of following two:
(1) electronic type type analysis is carried out for file destination identification to the file destination in file including video content
Video classification, particular, it is important that the accumulated result based on children's number of objects each in each video image is realized to target
File whether be plays for children evaluation；
(2) resolution based on the high-definition image maps the default sliding window of corresponding size, and based on described default
The channel the R numeric distribution situation of pixel in sliding window in all directions determines each channel the RGB of pixel processed
Data processing mode, so as to obtain it is most effective carry out image filtering referential data.
According to an aspect of the present invention, a kind of video file Command Line Parsing method is provided, this method includes using a kind of view
Frequency file Command Line Parsing system parses video file, and the video file Command Line Parsing system includes: scene display equipment, use
In when receiving the plays for children identification signal, red text corresponding with the plays for children identification signal is shown；Video is deposited
Equipment is stored up, for video file data library to be stored in advance, the video file data library saves each video file folder, each
Single target file and configuration corresponding with file destination text including video content are placed in a video file folder
Part.
More specifically, in the video file Command Line Parsing system, further includes:
File searches equipment, for according to the user's choice, obtaining the video files names chosen by user, is based on institute
It states video files names and finds corresponding video file folder in video file data library, obtained from video file folder
File destination including video content, and play the file destination.
More specifically, in the video file Command Line Parsing system, further includes:
Document analysis equipment is searched equipment with the file and connect, for obtain video file folder it is interior with it is described
The corresponding configuration file of file destination reads the configuration file to obtain the corresponding run-out duration；Image interception equipment,
It searches equipment and the document analysis equipment with the file respectively connect, for being based on the run-out duration from described
Interception is in each frame image of run-out position in file destination, using each frame image in run-out position as contents extraction figure
As output.
More specifically, in the video file Command Line Parsing system, further includes:
Pixel analytical equipment is connect, for receiving the contents extraction image, to described with described image interception equipment
Each pixel in contents extraction image carries out the judgement of noise spot, to determine each pixel as noise spot or non-noise
Point, wherein the pixel analytical equipment detects the various noises in the contents extraction image, to obtain in described
Hold each noise region extracted in image, the pixel being located in some noise region is confirmed as noise spot, will be located at
Pixel except each noise region is confirmed as non-noise point；Resolution measuring device is mentioned for receiving the content
Image is taken, for extracting the resolution of the contents extraction image, and based on the mapping pair of the resolution of the contents extraction image
Answer the default sliding window of size, wherein the resolution of the contents extraction image is bigger, the diameter of the default sliding window of mapping
It is bigger to length；Dynamic processing equipment is connect with the resolution measuring device, for obtaining the default sliding window, and
Dynamic filter processing is carried out to each of contents extraction image pixel；The dynamic processing equipment is to the content
Extracting each of image pixel and carrying out dynamic filter processing includes: by each of contents extraction image pixel
It selects as subject image vegetarian refreshments, determines in the contents extraction image using the subject image vegetarian refreshments as in the default sliding window of centroid
Each pixel using as each pixel to be assessed, calculating is with the subject image vegetarian refreshments in the default sliding window
The mean square deviation of each pixel R channel value to be assessed after excluding the subject image vegetarian refreshments in the horizontal direction at center calculates
It is each after excluding the subject image vegetarian refreshments in vertical direction in the default sliding window centered on the subject image vegetarian refreshments
The mean square deviation of a pixel R channel value to be assessed calculates in the default sliding window centered on the subject image vegetarian refreshments
Leading diagonal direction on exclude the mean square deviation of each pixel R channel value to be assessed after the subject image vegetarian refreshments, calculate and exist
After excluding the subject image vegetarian refreshments on counter-diagonal direction in the default sliding window centered on the subject image vegetarian refreshments
Each pixel R channel value to be assessed mean square deviation, the minimum value in four mean square deviations is obtained, by the minimum value pair
Answer the mean value of each pixel R channel value to be assessed after excluding the subject image vegetarian refreshments on direction as the subject image vegetarian refreshments
Processed R channel value, each pixel G to be assessed after the subject image vegetarian refreshments will be excluded on the minimum value corresponding direction
Processed G channel value of the mean value of channel value as the subject image vegetarian refreshments, described in being excluded on the minimum value corresponding direction
Processed channel B value of the mean value of each pixel channel B value to be assessed after subject image vegetarian refreshments as the subject image vegetarian refreshments；
Signal integration equipment is connect with the dynamic processing equipment, for based on each of contents extraction image pixel
Processed R channel value, that processed G channel value and processed channel B value obtain the contents extraction image is corresponding processed
Image；Region segmentation equipment is connect with the signal integration equipment, for receiving each frame processed image, has been located to described
Reason image executes following movement: based on default human body gray threshold recognize in the processed image each pixel whether be
Human body pixel point forms one or more subgraphs based on each pixel in the processed image, is based on children's figure
Feature determines whether each subgraph corresponds to children's object, to obtain the children's object quantity in the processed image；Number
Analyzing device is measured, is connect with the region segmentation equipment, for receiving each children's number of objects in each processed image
And added up that children's sum is obtained evaluation reference value divided by the quantity of processed image to obtain children's sum；Children
Play identification equipment, connect, in the evaluation reference value respectively with the scene display equipment and the quantity analyzing device
When more than limitation, plays for children identification signal is issued.
Detailed description of the invention
Embodiment of the present invention is described below with reference to attached drawing, in which:
Fig. 1 is to be intercepted according to the image interception equipment of the video file Command Line Parsing system shown in embodiment of the present invention
The data structure diagram of contents extraction image.
Specific embodiment
Embodiment of the present invention is described in detail below with reference to accompanying drawings.
Video file is one of internet multimedia important content.It refers mainly to those and contains real-time audio, video
The multimedia file of information, multimedia messages are typically derived from video input apparatus.Video refers to a series of static images
The various technologies captured, noted down in a manner of electric signal, handled, stored, transmitted and reappeared.Continuous image change is per second
When more than more than 24 frames (frame) picture, according to persistence of vision principle, human eye can not distinguish the tableaux of single width；It seems
It is smooth continuous visual effect, picture continuous in this way is called video.Video technique is developed for television system earliest,
But it has developed into a variety of different formats now videograph gets off with sharp consumer.The prosperity of network technology also promotes to regard
The record segment of frequency is present on internet in the form of streaming media and can be received and be played by computer.Video and film category
In different technologies, the latter be using photography by dynamic image capturing be a series of still photo.
In order to overcome above-mentioned deficiency, the present invention builds a kind of video file Command Line Parsing method, and this method includes using one
Video file Command Line Parsing system is planted to parse video file.The video file Command Line Parsing system can effectively solve the problem that accordingly
The technical issues of.
Fig. 1 is to be intercepted according to the image interception equipment of the video file Command Line Parsing system shown in embodiment of the present invention
The data structure diagram of contents extraction image.
The video file Command Line Parsing system shown according to an embodiment of the present invention includes:
Scene display equipment, for when receiving the plays for children identification signal, display to be believed with plays for children identification
Number corresponding red text；
Video storaging equipment, for video file data library to be stored in advance, the video file data library saves each
Video file folder, be placed in each video file folder single target file including video content and with the target text
The corresponding configuration file of part.
Then, continue that the specific structure of video file Command Line Parsing system of the invention is further detailed.
In the video file Command Line Parsing system, further includes:
File searches equipment, for according to the user's choice, obtaining the video files names chosen by user, is based on institute
It states video files names and finds corresponding video file folder in video file data library, obtained from video file folder
File destination including video content, and play the file destination.
In the video file Command Line Parsing system, further includes:
Document analysis equipment is searched equipment with the file and connect, for obtain video file folder it is interior with it is described
The corresponding configuration file of file destination reads the configuration file to obtain the corresponding run-out duration；
Image interception equipment searches equipment with the file respectively and the document analysis equipment is connect, for being based on
The run-out duration intercepts each frame image in run-out position from the file destination, will be every in run-out position
One frame image is exported as contents extraction image.
In the video file Command Line Parsing system, further includes:
Pixel analytical equipment is connect, for receiving the contents extraction image, to described with described image interception equipment
Each pixel in contents extraction image carries out the judgement of noise spot, to determine each pixel as noise spot or non-noise
Point, wherein the pixel analytical equipment detects the various noises in the contents extraction image, to obtain in described
Hold each noise region extracted in image, the pixel being located in some noise region is confirmed as noise spot, will be located at
Pixel except each noise region is confirmed as non-noise point；
Resolution measuring device, for receiving the contents extraction image, for extracting the solution of the contents extraction image
Analysis degree, and the default sliding window for corresponding to size is mapped based on the resolution of the contents extraction image, wherein the content mentions
Take the resolution of image bigger, the radical length of the default sliding window of mapping is bigger；
Dynamic processing equipment is connect with the resolution measuring device, for obtaining the default sliding window, and to institute
It states each of contents extraction image pixel and carries out dynamic filter processing；
The dynamic processing equipment carries out dynamic filter processing packet to each of contents extraction image pixel
Include: using each of contents extraction image pixel as subject image vegetarian refreshments, determine in the contents extraction image with
The subject image vegetarian refreshments is each pixel in the default sliding window of centroid to calculate and exist as each pixel to be assessed
It is each after excluding the subject image vegetarian refreshments in horizontal direction in the default sliding window centered on the subject image vegetarian refreshments
The mean square deviation of a pixel R channel value to be assessed calculates in the default sliding window centered on the subject image vegetarian refreshments
Vertical direction on exclude the mean square deviation of each pixel R channel value to be assessed after the subject image vegetarian refreshments, calculate described
It is each after excluding the subject image vegetarian refreshments on leading diagonal direction in default sliding window centered on the subject image vegetarian refreshments
The mean square deviation of a pixel R channel value to be assessed calculates in the default sliding window centered on the subject image vegetarian refreshments
Counter-diagonal direction on exclude the mean square deviation of each pixel R channel value to be assessed after the subject image vegetarian refreshments, obtain institute
The minimum value in four mean square deviations is stated, will be excluded on the minimum value corresponding direction each to be assessed after the subject image vegetarian refreshments
Processed R channel value of the mean value of pixel R channel value as the subject image vegetarian refreshments will arrange on the minimum value corresponding direction
Except processed G of the mean value as the subject image vegetarian refreshments of each pixel G channel value to be assessed after the subject image vegetarian refreshments
Channel value will exclude each pixel channel B value to be assessed after the subject image vegetarian refreshments on the minimum value corresponding direction
Processed channel B value of the mean value as the subject image vegetarian refreshments；
Signal integration equipment is connect with the dynamic processing equipment, for based on each in the contents extraction image
It is corresponding that processed R channel value, processed G channel value and the processed channel B value of a pixel obtain the contents extraction image
Processed image；
Region segmentation equipment is connect with the signal integration equipment, for receiving each frame processed image, to it is described
It handles image and executes following movement: whether each pixel is recognized in the processed image based on default human body gray threshold
For human body pixel point, one or more subgraphs are formed based on each pixel in the processed image, are based on children's body
Type feature determines whether each subgraph corresponds to children's object, to obtain the children's object quantity in the processed image；
Quantity analyzing device is connect with the region segmentation equipment, for receiving oneself in each processed image
Virgin number of objects is simultaneously added up to obtain children's sum, and children's sum is obtained evaluation ginseng divided by the quantity of processed image
Examine value；
Plays for children identifies equipment, connect respectively with the scene display equipment and the quantity analyzing device, in institute
When commentary valence reference value is more than limitation, plays for children identification signal is issued.
In the video file Command Line Parsing system: the plays for children identification equipment is also used in the evaluation reference value
When being less than limitation, the unidentified signal of plays for children is issued.
In the video file Command Line Parsing system: the dynamic processing equipment includes the sub- equipment of data receiver, level
The sub- equipment of Direction estimation, vertical direction are assessed sub- equipment, the sub- equipment of leading diagonal Direction estimation, counter-diagonal Direction estimation and are set
Standby and data export sub- equipment.
In the video file Command Line Parsing system: the leading diagonal direction is with from the default sliding window
Direction of the lower left corner to the upper right corner of the default sliding window.
In the video file Command Line Parsing system: the counter-diagonal direction is with from the default sliding window
Direction of the lower right corner to the upper left corner of the default sliding window.
In addition, the plays for children identification lectotype selection is graphics processor.Graphics processor (English: Graphics
Processing Unit, abbreviation: GPU), it also known as shows core, vision processor, display chip, is a kind of specially in personal electricity
The micro process that image operation works in brain, work station, game machine and some mobile devices (such as tablet computer, smart phone)
Device.
Graphics processor purposes is will to show that information carries out conversion driving required for computer system, and mention to display
For line scan signals, the correct display of display is controlled, is the critical elements of connection display and PC mainboard, and
One of the important equipment of " human-computer dialogue ".Video card undertakes output display figure as an important component in host computer
The task of shape, video card is extremely important for the people for being engaged in professional graphic design.
The processor of video card is known as graphics processor (GPU), it is video card " heart ", similar with CPU, only GPU
It is to aim to execute complicated mathematics and geometry calculating and design, these calculating are necessary to figure rendering.It is certain most quick
The integrated number of transistors of GPU be even more than common CP U.
Using video file Command Line Parsing system of the invention, difficult for every Digital video resolution in the prior art
Technical problem, by carrying out electronic type type analysis to the file destination in file including video content as file destination mirror
Video classification is determined, particular, it is important that the accumulated result based on children's number of objects each in each video image is realized to mesh
Mark file whether be plays for children evaluation；Meanwhile the resolution also based on the high-definition image maps the default cunning of corresponding size
Dynamic window, and located based on the determination of the channel the R numeric distribution situation of the pixel in all directions in the default sliding window
The data processing mode in each channel RGB of pixel is managed, so as to obtain the most effective reference number for carrying out image filtering
Value.
It is understood that although the present invention has been disclosed in the preferred embodiments as above, above-described embodiment not to
Limit the present invention.For any person skilled in the art, without departing from the scope of the technical proposal of the invention,
Many possible changes and modifications all are made to technical solution of the present invention using the technology contents of the disclosure above, or are revised as
With the equivalent embodiment of variation.Therefore, anything that does not depart from the technical scheme of the invention are right according to the technical essence of the invention
Any simple modifications, equivalents, and modifications made for any of the above embodiments still fall within the range of technical solution of the present invention protection
It is interior.
Claims (8)
1. a kind of video file Command Line Parsing method, this method includes that view is parsed using a kind of video file Command Line Parsing system
Frequency file, which is characterized in that the video file Command Line Parsing system includes:
Scene display equipment, for showing and the plays for children identification signal pair when receiving the plays for children identification signal
The red text answered；
Video storaging equipment, for video file data library to be stored in advance, the video file data library saves each video
File, be placed in each video file folder single target file including video content and with the file destination pair
The configuration file answered.
2. the method as described in claim 1, which is characterized in that the system also includes:
File searches equipment, for according to the user's choice, obtaining the video files names chosen by user, is based on the view
Frequency file title finds corresponding video file folder in video file data library, obtains from video file folder and includes
The file destination of video content, and play the file destination.
3. method according to claim 2, which is characterized in that the system also includes:
Document analysis equipment is searched equipment with the file and is connect, and presss from both sides the interior and target for obtaining the video file
The corresponding configuration file of file reads the configuration file to obtain the corresponding run-out duration；
Image interception equipment searches equipment with the file respectively and the document analysis equipment is connect, for based on described
The run-out duration intercepts each frame image in run-out position from the file destination, will be in each frame of run-out position
Image is exported as contents extraction image.
4. method as claimed in claim 3, which is characterized in that the system also includes:
Pixel analytical equipment is connect, for receiving the contents extraction image, to the content with described image interception equipment
The judgement that each pixel in image carries out noise spot is extracted, using each determining pixel as noise spot or non-noise point,
Wherein, the pixel analytical equipment detects the various noises in the contents extraction image, to obtain the content
Each noise region in image is extracted, the pixel being located in some noise region is confirmed as noise spot, institute will be located at
It states the pixel except each noise region and is confirmed as non-noise point；
Resolution measuring device, for receiving the contents extraction image, for extracting the resolution of the contents extraction image,
And the default sliding window of corresponding size is mapped based on the resolution of the contents extraction image, wherein the contents extraction figure
The resolution of picture is bigger, and the radical length of the default sliding window of mapping is bigger；
Dynamic processing equipment is connect with the resolution measuring device, for obtaining the default sliding window, and to described interior
Hold and extracts the pixel progress dynamic filter processing of each of image；
The dynamic processing equipment to each of contents extraction image pixel carry out dynamic filter processing include: by
Each of contents extraction image pixel determines in the contents extraction image as subject image vegetarian refreshments with described right
It is each pixel in the default sliding window of centroid as pixel to calculate described pre- as each pixel to be assessed
If being excluded in the horizontal direction in sliding window centered on the subject image vegetarian refreshments each to be evaluated after the subject image vegetarian refreshments
Estimate the mean square deviation of pixel R channel value, calculates vertical centered on the subject image vegetarian refreshments in the default sliding window
The mean square deviation of each pixel R channel value to be assessed after excluding the subject image vegetarian refreshments on direction is calculated in the default cunning
It is each to be evaluated after excluding the subject image vegetarian refreshments on leading diagonal direction in dynamic window centered on the subject image vegetarian refreshments
Estimate the mean square deviation of pixel R channel value, the pair calculated in the default sliding window centered on the subject image vegetarian refreshments is right
The mean square deviation of each pixel R channel value to be assessed after excluding the subject image vegetarian refreshments on linea angulata direction obtains described four
Minimum value in mean square deviation will exclude each pixel to be assessed after the subject image vegetarian refreshments on the minimum value corresponding direction
Processed R channel value of the mean value of R channel value as the subject image vegetarian refreshments, described in being excluded on the minimum value corresponding direction
Processed G channel value of the mean value of each pixel G channel value to be assessed after subject image vegetarian refreshments as the subject image vegetarian refreshments,
To be excluded on the minimum value corresponding direction mean value of each pixel channel B value to be assessed after the subject image vegetarian refreshments as
The processed channel B value of the subject image vegetarian refreshments；
Signal integration equipment is connect with the dynamic processing equipment, for based on each of contents extraction image picture
It is corresponding that processed R channel value, processed G channel value and the processed channel B value of vegetarian refreshments obtain the contents extraction image
Handle image；
Region segmentation equipment is connect with the signal integration equipment, for receiving each frame processed image, to described processed
Image executes following movement: recognizing whether each pixel in the processed image is people based on default human body gray threshold
Body image vegetarian refreshments forms one or more subgraphs based on each pixel in the processed image, special based on children's figure
It levies and determines whether each subgraph corresponds to children's object, to obtain the children's object quantity in the processed image；
Quantity analyzing device is connect with the region segmentation equipment, for receiving each children couple in each processed image
As quantity and added up to obtain children's sum, by children's sum divided by the quantity of processed image to obtain evaluation reference
Value；
Plays for children identifies equipment, connect respectively with the scene display equipment and the quantity analyzing device, in institute's commentary
When valence reference value is more than limitation, plays for children identification signal is issued.
5. method as claimed in claim 4, it is characterised in that:
The plays for children identification equipment is also used to when the evaluation reference value is less than limitation, issues the unidentified letter of plays for children
Number.
6. method as claimed in claim 5, it is characterised in that:
The dynamic processing equipment include the sub- equipment of data receiver, horizontal direction assesses sub- equipment, vertical direction assesses sub- equipment,
The sub- equipment of leading diagonal Direction estimation, the sub- equipment of counter-diagonal Direction estimation and data export sub- equipment.
7. method as claimed in claim 6, it is characterised in that:
The leading diagonal direction is from the lower left corner of the default sliding window to the upper right corner of the default sliding window
Direction.
8. the method as described in claim 5-7 is any, it is characterised in that:
The counter-diagonal direction is from the lower right corner of the default sliding window to the upper left corner of the default sliding window
Direction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810944771.4A CN109788346B (en) | 2018-08-19 | 2018-08-19 | Video file configuration analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810944771.4A CN109788346B (en) | 2018-08-19 | 2018-08-19 | Video file configuration analysis method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109788346A true CN109788346A (en) | 2019-05-21 |
| CN109788346B CN109788346B (en) | 2021-01-22 |
Family
ID=66496263
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810944771.4A Expired - Fee Related CN109788346B (en) | 2018-08-19 | 2018-08-19 | Video file configuration analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109788346B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070061352A1 (en) * | 2003-12-03 | 2007-03-15 | Koninklijke Philips Electronic, N.V. | System & method for integrative analysis of intrinsic and extrinsic audio-visual |
| CN101883230A (en) * | 2010-05-31 | 2010-11-10 | 中山大学 | Digital television actor retrieval method and system |
| CN101981576A (en) * | 2008-03-31 | 2011-02-23 | 杜比实验室特许公司 | Associating information with media content using objects recognized therein |
| CN103714094A (en) * | 2012-10-09 | 2014-04-09 | 富士通株式会社 | Equipment and method for recognizing objects in video |
| CN103870513A (en) * | 2012-12-18 | 2014-06-18 | 华为技术有限公司 | Method, equipment and system for video processing |
-
2018
- 2018-08-19 CN CN201810944771.4A patent/CN109788346B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070061352A1 (en) * | 2003-12-03 | 2007-03-15 | Koninklijke Philips Electronic, N.V. | System & method for integrative analysis of intrinsic and extrinsic audio-visual |
| CN101981576A (en) * | 2008-03-31 | 2011-02-23 | 杜比实验室特许公司 | Associating information with media content using objects recognized therein |
| CN101883230A (en) * | 2010-05-31 | 2010-11-10 | 中山大学 | Digital television actor retrieval method and system |
| CN103714094A (en) * | 2012-10-09 | 2014-04-09 | 富士通株式会社 | Equipment and method for recognizing objects in video |
| CN103870513A (en) * | 2012-12-18 | 2014-06-18 | 华为技术有限公司 | Method, equipment and system for video processing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109788346B (en) | 2021-01-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3886448A1 (en) | Video processing method and device, electronic equipment and computer readable medium | |
| US6526161B1 (en) | System and method for biometrics-based facial feature extraction | |
| KR20180112848A (en) | Information processing method and terminal | |
| US20190222806A1 (en) | Communication system and method | |
| CN101783886A (en) | Information processing apparatus, information processing method, and program | |
| US8218025B2 (en) | Image capturing apparatus, image capturing method, and computer program product | |
| JP2003525504A (en) | System and method for locating an object in an image using a model | |
| JP5178611B2 (en) | Image processing apparatus, image processing method, and program | |
| KR101081494B1 (en) | facial physiognomic judgment of fortune and face avatar generation method using a face recognition and system thereof | |
| KR102195642B1 (en) | Terminal and apparatus for providing search information based on color information | |
| JP2006155238A (en) | Information processor, processing method, and processing program, portable terminal, and computer-readable recording medium | |
| WO2014100936A1 (en) | Method, platform, and system for manufacturing associated information library of video and for playing video | |
| WO2013181108A2 (en) | Video transmission and reconstruction | |
| EP1820158B1 (en) | Album creating apparatus, album creating method, and album creating program | |
| CN109286848B (en) | Terminal video information interaction method and device and storage medium | |
| CN103945140A (en) | Method and system for generating video captions | |
| CN108076359B (en) | Business object display method and device and electronic equipment | |
| CN109309868B (en) | Video file Command Line Parsing system | |
| CN109511010A (en) | Method for processing video frequency, video process apparatus, electronic equipment and storage medium | |
| AU2016312847A1 (en) | A process, system and apparatus for machine colour characterisation of digital media | |
| US20230031999A1 (en) | Emoticon generating device | |
| CN109788346A (en) | Video file Command Line Parsing method | |
| EP3783561A1 (en) | Information processing device, information processing system, information processing method, and program | |
| KR102482841B1 (en) | Artificial intelligence mirroring play bag | |
| CN113052067A (en) | Real-time translation method, device, storage medium and terminal equipment |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201225 Address after: 2105Q, 21 / F, Shihong building, 2095 Nanlian Bixin Road, Longgang street, Longgang District, Shenzhen, Guangdong 518000 Applicant after: Shenzhen Liangzi Technology Co.,Ltd. Address before: 215347 No. 317 Qianjin West Road, Kunshan City, Suzhou City, Jiangsu Province Applicant before: Zhu Liping |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210122 Termination date: 20210819 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |