CN109309863B - Movie contents matching mechanism for seedlings - Google Patents
Movie contents matching mechanism for seedlings Download PDFInfo
- Publication number
- CN109309863B CN109309863B CN201810860054.3A CN201810860054A CN109309863B CN 109309863 B CN109309863 B CN 109309863B CN 201810860054 A CN201810860054 A CN 201810860054A CN 109309863 B CN109309863 B CN 109309863B
- Authority
- CN
- China
- Prior art keywords
- run
- equipment
- image
- background music
- pixel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000033764 rhythmic process Effects 0.000 claims abstract description 21
- 238000001914 filtration Methods 0.000 claims description 27
- 238000000605 extraction Methods 0.000 claims description 11
- 238000007493 shaping process Methods 0.000 claims description 7
- 239000000203 mixture Substances 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 5
- 238000004040 coloring Methods 0.000 description 3
- 230000005611 electricity Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000003139 buffering effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000000034 method Methods 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
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
-
- 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
- H04N21/435—Processing of additional data, e.g. decrypting of additional data, reconstructing software from modules extracted from the transport stream
-
- 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
- H04N21/439—Processing of audio elementary streams
-
- 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
- H04N21/81—Monomedia components thereof
- H04N21/8106—Monomedia components thereof involving special audio data, e.g. different tracks for different languages
- H04N21/8113—Monomedia components thereof involving special audio data, e.g. different tracks for different languages comprising music, e.g. song in MP3 format
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a kind of movie contents matching mechanism for seedlings, it include: classification storage equipment, run-out for various different rhythm grades to be stored in advance is dubbed in background music, and content of the content that the run-out of various difference rhythm grades is dubbed in background music all with the cinematic data of pin-saving chip storage matches；It dubs in background music and selects equipment, for receiving the movement rank of film, and run-out corresponding with the movement rank of the film is searched in the classification storage equipment based on the movement rank of the film and is dubbed in background music, the rhythm grade that the run-out found is dubbed in background music is corresponding with the movement rank of the film；It dubs in background music replacement equipment, equipment is selected to connect with described dub in background music, it updates the run-out in the pin-saving chip for being dubbed in background music based on the run-out found and dubs in background music, played so that the run-out found is dubbed in background music for the next time of the cinematic data of pin-saving chip storage.Through the invention, the level of film making is improved.
Description
Technical field
The present invention relates to film making field more particularly to a kind of movie contents matching mechanism for seedlings.
Background technique
Film is according to persistence of vision principle, with photograph (and recording) means the image (and sound) of extraneous things
It shoots with video-corder on film, by projection (while also original sound), the mode of electricity consumption projects activity video in screen (and synchronous
Sound) to show the modern technologies of certain content.Film is a kind of vision and auditory art, utilizes film, video-tape or numerical digit
Media are by image and voice capture, along with the editing in later period forms.Film is a kind of modern art of synthesis, also as
Art itself has complicated and numerous departments.Film is one kind using modern scientific and technical result as DO-IT-YOURSELF DIY, is regarded with creating
Feel image and montage expression means, in the room and time of screen, mould movement, sound draw combine, it is true to nature
Concrete image, to reflect the modern art of social life.Film can accurately " restore " real world, " showing " virtual world,
Give realism, friendliness, just like it is on the spot in person.This characteristic of film, can satisfy that people are broader, more realistically feel
The hope lived.The frame rate of film is usually that 24 frames are per second, with the promotion of technology, i.e., it is every 48 frames even 60 frames will occurs
The film of second.
Summary of the invention
In order to solve rhythm grade and film that run-out in the prior art is dubbed in background music movement rank can not matched technology ask
Topic, the present invention provides a kind of movie contents matching mechanism for seedlings.
For this purpose, the present invention at least has the important inventive point of following two:
(1) run-out that various different rhythm grades are stored in advance is dubbed in background music, and the run-out of various difference rhythm grades is dubbed in background music interior
The content of the cinematic data of Rong Douyu pin-saving chip storage matches；The movement rank of film is in the classification storage equipment
It is middle to search corresponding with the movement rank of film run-out and dub in background music, the rhythm grade that the run-out found is dubbed in background music with it is described
The movement rank of film is corresponding, and updates run-out and dub in background music so that the run-out found to be dubbed in background music and is used for the data storage core
The next time of the cinematic data of piece storage plays；
(2) depth of field value and size of target each in image are parsed, with the target phase based on most shallow depth of field value
Pixel sum corresponding to the target pattern answered determines the pixel sum that sliding window occupies, also based on most shallow depth of field value
The shape of the corresponding target pattern of target determine the shape of the sliding window, to realize the specific aim of image content-based
Image procossing.
According to an aspect of the present invention, a kind of movie contents matching mechanism for seedlings is provided, the mechanism includes:
Classification storage equipment, the run-out for various different rhythm grades to be stored in advance are dubbed in background music, various difference rhythm grades
Content of the content dubbed in background music of run-out all with the cinematic data of pin-saving chip storage match.
More specifically, in the movie contents matching mechanism for seedlings, further includes:
It dubs in background music and selects equipment, connect with the classification storage equipment, for receiving the movement rank of film, and based on described
The movement rank of film searches run-out corresponding with the movement rank of the film in the classification storage equipment and dubs in background music, described
The rhythm grade that the run-out found is dubbed in background music is corresponding with the movement rank of the film.
More specifically, in the movie contents matching mechanism for seedlings, further includes:
Dub in background music replacement equipment, select equipment to connect with described dub in background music, for dubbed in background music based on the run-out found update it is described
Run-out in pin-saving chip is dubbed in background music, so that the run-out found is dubbed in background music for pin-saving chip storage
The next time of cinematic data plays.
More specifically, in the movie contents matching mechanism for seedlings, further includes:
Overflow checking equipment is connect with live buffer memory device, is overflow for detecting the buffering inside the live buffer memory device
Artificial situation, and when there is Buffer Overflow situation, issue corresponding alarm signal；Chip reads interface, stores respectively with data
Chip and the live buffer memory device are separately connected, and the cinematic data for storing the pin-saving chip reads and sends
Into the live buffer memory device；Live buffer memory device, for caching the cinematic data that will be played, the cinematic data is by more
A moving-picture frame composition, wherein each moving-picture frame has corresponding frame number, and the moving-picture frame played at first is cached at first and corresponded to
Frame number it is smaller；Run-out intercepts equipment, connect with the live buffer memory device, for grab frame number rank behind it is each
Moving-picture frame grabs image for use as run-out, and exports each run-out crawl image；Entropy analyzing device is cut with the run-out
It takes equipment to connect, for receiving each run-out crawl image, parses the entropy of each run-out crawl image, and compare
Each entropy of each run-out crawl image is exported using the smallest run-out crawl image of entropy as high value image；Mesh
Extract equipment is marked, connect with the entropy analyzing device, for receiving the high value image, obtains in the high value image
Each edge line, each target in the high value image is synthesized based on each group of edge lines, and in the high price
The corresponding target pattern of each target for only including single target is determined in value image respectively；Depth of field analyzing device,
It is connect with the Objective extraction equipment, for receiving each target pattern, and determines that each target pattern is corresponding respectively
Target depth of field value in the high value image exports the corresponding each depth of field value of each target；Size analyzing device, with
The Objective extraction equipment connection, for receiving each target pattern, and determines the composition of each target pattern respectively
The sum of pixel, and the corresponding each pixel sum of each target pattern；Window shaping device, respectively with the scape
Deep analyzing device is connected with the size analyzing device, for receiving the corresponding each depth of field value of each target and each mesh
The corresponding each pixel of case of marking on a map is total, picture corresponding to the corresponding target pattern of target based on most shallow depth of field value
Vegetarian refreshments sum determines the pixel sum that sliding window occupies, the corresponding target pattern of target also based on most shallow depth of field value
Shape determines the shape of the sliding window；Weighted filtering equipment shapes with the Objective extraction equipment and the window respectively
Equipment connection, it is dynamic for executing following weighted filtering for the color component value of each of high value image pixel
Make: determining each pixel nearby of each of high value image pixel based on the sliding window, obtain each
Each color component value of a pixel nearby is weighted filtering to each color component value of each pixel nearby
It handles to obtain the amendment color component value of each of high value image pixel；Output equipment is filtered, and it is described
The connection of weighted filtering equipment, obtains simultaneously for the amendment color component value based on each of high value image pixel
Output amendment image；Performer's identification apparatus is connect with the filtering output equipment, for receiving the amendment image, based on pre-
If benchmark human body pattern identifies from the amendment image and is partitioned into each performer's subgraph；Grade acquire equipment, respectively with
Described dub in background music selects equipment to connect with performer's identification apparatus, for receiving each performer's subgraph, drills each
Member's subgraph carries out posture detection to determine corresponding movement rank, each movement grade corresponding to each performer's subgraph
Not carry out mean value computation to obtain the movement rank of the film of the live buffer memory device caching.
More specifically, in the movie contents matching mechanism for seedlings: the weighted filtering equipment is to each pixel nearby
Each color component value of point is weighted filtering processing to obtain the amendment of each of high value image pixel
Color component value include: apart from each of high value image pixel it is closer near pixel, color component
It is bigger that value participates in weighted value used in weighted filtering processing.
More specifically, in the movie contents matching mechanism for seedlings: the weighted filtering equipment is to each pixel nearby
Each color component value of point is weighted filtering processing to obtain the amendment of each of high value image pixel
Color component value further include: each power based on each each color component value of pixel nearby and each pixel nearby
Weight values execute weighted median processing, to obtain the amendment color component value of each of high value image pixel.
More specifically, in the movie contents matching mechanism for seedlings: in the window shaping device, based on the most shallow depth of field
The shape of the corresponding target pattern of the target of value determines that the shape of the sliding window includes: the mesh to the most shallow depth of field value
The shape for marking corresponding target pattern is zoomed in and out to obtain the sliding window.
More specifically, in the movie contents matching mechanism for seedlings: in run-out interception equipment, frame number ranks behind
The play time section that occupies of each moving-picture frame be 10 minutes.
More specifically, in the movie contents matching mechanism for seedlings: being selected in equipment in described dub in background music, the movement of the film
Rank is higher, and the rhythm faster grade that the run-out found is dubbed in background music.
Detailed description of the invention
Embodiment of the present invention is described below with reference to attached drawing, in which:
Fig. 1 is more to be stored according to the live buffer memory device of the movie contents matching mechanism for seedlings shown in embodiment of the present invention
Frame cinematic data.
Specific embodiment
The embodiment of movie contents matching mechanism for seedlings of the invention is described in detail below with reference to accompanying drawings.
Film is to combine a kind of continuous image frame to grow up by activity photography and diaprojection art, is one
Door vision and the sense of hearing modern art and one can accommodate drama, photography, drawing, music, dancing, text, sculpture, build
The modern science and technology of a variety of art and the synthesis of art such as build.But he has feature alone again, and film is on artistic expression
Not only with the feature of various other art, and the electricity because montage (French: Montage) this artistry jumping can be used
Shadow group connects skill, has the expression means for surmounting all other art, and film can be shown with massive duplication, with modern society
The development of meeting, it is the indispensable a part of people's daily life that film, which has been deep into the every aspect of human society life,.
In order to overcome above-mentioned deficiency, the present invention has built a kind of movie contents matching mechanism for seedlings, can effectively solve the problem that corresponding
Technical problem.
Fig. 1 is more to be stored according to the live buffer memory device of the movie contents matching mechanism for seedlings shown in embodiment of the present invention
Frame cinematic data.
The movie contents matching mechanism for seedlings shown according to an embodiment of the present invention includes:
Classification storage equipment, the run-out for various different rhythm grades to be stored in advance are dubbed in background music, various difference rhythm grades
Content of the content dubbed in background music of run-out all with the cinematic data of pin-saving chip storage match.
Then, continue that the specific structure of movie contents matching mechanism for seedlings of the invention is further detailed.
In the movie contents matching mechanism for seedlings, further includes:
It dubs in background music and selects equipment, connect with the classification storage equipment, for receiving the movement rank of film, and based on described
The movement rank of film searches run-out corresponding with the movement rank of the film in the classification storage equipment and dubs in background music, described
The rhythm grade that the run-out found is dubbed in background music is corresponding with the movement rank of the film.
In the movie contents matching mechanism for seedlings, further includes:
Dub in background music replacement equipment, select equipment to connect with described dub in background music, for dubbed in background music based on the run-out found update it is described
Run-out in pin-saving chip is dubbed in background music, so that the run-out found is dubbed in background music for pin-saving chip storage
The next time of cinematic data plays.
In the movie contents matching mechanism for seedlings, further includes:
Overflow checking equipment is connect with live buffer memory device, is overflow for detecting the buffering inside the live buffer memory device
Artificial situation, and when there is Buffer Overflow situation, issue corresponding alarm signal；
Chip reads interface, is separately connected respectively with pin-saving chip and the live buffer memory device, and being used for will be described
The cinematic data of pin-saving chip storage reads and is sent in the live buffer memory device；
Live buffer memory device, for caching the cinematic data that will be played, the cinematic data is made of multiple moving-picture frames,
Wherein, each moving-picture frame has corresponding frame number, and the moving-picture frame played at first caches at first and corresponding frame number is smaller；
Run-out intercepts equipment, connect with the live buffer memory device, each film to rank behind for grabbing frame number
Frame grabs image for use as run-out, and exports each run-out crawl image；
Entropy analyzing device is connect with run-out interception equipment, for receiving each run-out crawl image, parsing
The entropy of each run-out crawl image out, and each entropy of each run-out crawl image, entropy is the smallest
Run-out grabs image and exports as high value image；
Objective extraction equipment is connect with the entropy analyzing device, for receiving the high value image, obtains the height
The each edge line being worth in image, synthesizes each target in the high value image based on each group of edge lines, and
Determine the corresponding target pattern of each target for only including single target respectively in the high value image；
Depth of field analyzing device is connect with the Objective extraction equipment, true for receiving each target pattern, and respectively
Each fixed target pattern corresponds to target depth of field value in the high value image, exports the corresponding each scape of each target
Deep value；
Size analyzing device is connect with the Objective extraction equipment, true for receiving each target pattern, and respectively
The sum of the composition pixel of each fixed target pattern, and the corresponding each pixel sum of each target pattern；
Window shaping device is connect with the depth of field analyzing device and the size analyzing device respectively, each for receiving
A corresponding each depth of field value of target and the corresponding each pixel sum of each target pattern, based on most shallow scape
Pixel sum corresponding to the corresponding target pattern of the target being worth deeply determines the pixel sum that sliding window occupies, and is also based on
The shape of the corresponding target pattern of the target of most shallow depth of field value determines the shape of the sliding window；
Weighted filtering equipment is connect with the Objective extraction equipment and the window shaping device respectively, for being directed to institute
The color component value for stating each of high value image pixel executes following weighted filtering movement: based on the sliding window
The each pixel nearby for determining each of high value image pixel, obtains each face of each pixel nearby
Colouring component value is weighted filtering processing to each color component value of each pixel nearby to obtain the high value
The amendment color component value of each of image pixel；
Output equipment is filtered, is connect with the weighted filtering equipment, for based on each of described high value image
The amendment color component value of pixel obtains and exports amendment image；
Performer's identification apparatus is connect with the filtering output equipment, for receiving the amendment image, is based on preset reference
Human body pattern identifies from the amendment image and is partitioned into each performer's subgraph；
Grade acquires equipment, selects equipment and performer's identification apparatus to connect with described dub in background music respectively, for receiving
Each performer's subgraph is stated, posture detection is carried out to each performer's subgraph to determine corresponding movement rank, is drilled each
The corresponding each movement rank of member's subgraph carries out mean value computation to obtain the film of the live buffer memory device caching
Act rank.
In the movie contents matching mechanism for seedlings: each face of the weighted filtering equipment to each pixel nearby
Colouring component value is weighted filtering processing to obtain the amendment color component value of each of high value image pixel
Include: apart from each of high value image pixel it is closer near pixel, color component value participate in weighting
Weighted value used in being filtered is bigger.
In the movie contents matching mechanism for seedlings: each face of the weighted filtering equipment to each pixel nearby
Colouring component value is weighted filtering processing to obtain the amendment color component value of each of high value image pixel
Further include: each weighted value based on each each color component value of pixel nearby and each pixel nearby, which executes, to be added
Intermediate value processing is weighed, to obtain the amendment color component value of each of high value image pixel.
In the movie contents matching mechanism for seedlings: in the window shaping device, the target based on most shallow depth of field value
The shape of corresponding target pattern determines that the shape of the sliding window includes: corresponding to the target of the most shallow depth of field value
The shape of target pattern is zoomed in and out to obtain the sliding window.
In the movie contents matching mechanism for seedlings: being intercepted in equipment in the run-out, each electricity that frame number ranks behind
The play time section that shadow frame occupies is 10 minutes.
In the movie contents matching mechanism for seedlings: it is selected in equipment in described dub in background music, the movement rank of the film is higher,
The rhythm faster grade that the run-out found is dubbed in background music.
Furthermore it is possible to realize the grade acquisition equipment using dsp chip.The inside of dsp chip uses program sum number
According to separated Harvard structure, there is special hardware multiplier, pile line operation is widely used, special DSP instruction is provided, it can
To be used to quickly realize various digital signal processing algorithms.
According to the requirement of Digital Signal Processing, dsp chip generally has following some main features: (1) referring at one
Enable an achievable multiplication and a sub-addition in the period.(2) program and data space is separated, can simultaneously access instruction sum number
According to.(3) there is quick RAM in piece, can usually be accessed simultaneously in two pieces by independent data/address bus.(4) there is low overhead
Or without overhead loop and the hardware supported jumped.(5) quickly interrupt processing and Hardware I/O are supported.(6) have within the monocycle
Multiple hardware address generators of operation.(7) multiple operations can be executed parallel.(8) it supports pile line operation, makes fetching, translates
The operations such as code and execution can be with Overlapped Execution.
Classified according to the data format of dsp chip work.Data are known as pinpointing with the dsp chip that fixed point format works
Dsp chip, TMS320C1X/C2X, TMS320C2XX/C5X, TMS320C54X/C62XX such as TI company are serial, AD company
ADSP21XX series, the DSP16/16A of AT & T Corp., the MC56000 etc. of Motolora company.What is worked in a floating-point format is known as
Float-point DSP, the ADSP21XXX such as the TMS320C3X/C4X/C8X of TI company, AD company is serial, AT & T Corp.
The MC96002 etc. of DSP32/32C, Motolora company.
Using movie contents matching mechanism for seedlings of the invention, the rhythm grade dubbed in background music for run-out in the prior art and film
The technical issues of movement rank can not match, the run-out by the way that various different rhythm grades are stored in advance are dubbed in background music, various different sections
The content of content that the run-out of grade is dubbed in background music all with the cinematic data of pin-saving chip storage is played to match；The movement grade of film
It searches run-out corresponding with the movement rank of the film not in the classification storage equipment to dub in background music, the run-out found
The rhythm grade dubbed in background music is corresponding with the movement rank of the film, and updates run-out and dub in background music to match the run-out found
The next time of the happy cinematic data for pin-saving chip storage plays；It is particularly critical, to target each in image
Depth of field value and size parsed, it is total with pixel corresponding to the corresponding target pattern of target based on most shallow depth of field value
Number determines the pixel sum that sliding window occupies, and the shape of the corresponding target pattern of target also based on most shallow depth of field value is true
The shape of the fixed sliding window, to realize the specific aim image procossing of image content-based.
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 (2)
1. a kind of movie contents matching mechanism for seedlings, which is characterized in that the mechanism includes:
Classification storage equipment, the run-out for various different rhythm grades to be stored in advance are dubbed in background music, the piece of various difference rhythm grades
Content of the content that tail is dubbed in background music all with the cinematic data of pin-saving chip storage matches；
It dubs in background music and selects equipment, connect with the classification storage equipment, for receiving the movement rank of film, and be based on the film
Movement rank search run-out corresponding with the movement rank of the film in the classification storage equipment and dub in background music, the lookup
To the rhythm grade dubbed in background music of run-out it is corresponding with the movement rank of the film；
It dubs in background music replacement equipment, selects equipment to connect with described dub in background music, update the data for dubbing in background music based on the run-out found
Run-out in storage chip is dubbed in background music, the film for pin-saving chip storage so that the run-out found is dubbed in background music
The next time of data plays；
Overflow checking equipment is connect with live buffer memory device, for detecting the Buffer Overflow feelings inside the live buffer memory device
Condition, and when there is Buffer Overflow situation, issue corresponding alarm signal；
Chip reads interface, is separately connected, is used for the data with pin-saving chip and the live buffer memory device respectively
The cinematic data of storage chip storage reads and is sent in the live buffer memory device；
Live buffer memory device, for caching the cinematic data that will be played, the cinematic data is made of multiple moving-picture frames,
In, each moving-picture frame has corresponding frame number, and the moving-picture frame played at first caches at first and corresponding frame number is smaller；
Run-out intercepts equipment, connect with the live buffer memory device, for grab each moving-picture frame that frame number ranks behind with
Image is grabbed as run-out, and exports each run-out crawl image；
Entropy analyzing device is connect with run-out interception equipment, for receiving each run-out crawl image, is parsed every
The entropy of one run-out crawl image, and each entropy of each run-out crawl image, by the smallest run-out of entropy
Image is grabbed to export as high value image；
Objective extraction equipment is connect with the entropy analyzing device, for receiving the high value image, obtains the high value
Each edge line in image synthesizes each target in the high value image based on each group of edge lines, and in institute
It states in high value image and to determine the corresponding target pattern of each target for only including single target respectively；
Depth of field analyzing device is connect with the Objective extraction equipment, for receiving each target pattern, and is determined respectively every
One target pattern corresponds to target depth of field value in the high value image, exports the corresponding each depth of field of each target
Value；
Size analyzing device is connect with the Objective extraction equipment, for receiving each target pattern, and is determined respectively every
The sum of the composition pixel of one target pattern, and the corresponding each pixel sum of each target pattern；
Window shaping device is connect, for receiving each mesh respectively with the depth of field analyzing device and the size analyzing device
Corresponding each depth of field value and the corresponding each pixel sum of each target pattern are marked, based on most shallow depth of field value
The corresponding target pattern of target corresponding to pixel sum determine pixel sum that sliding window occupies, also based on most shallow
The shape of the corresponding target pattern of target of depth of field value determine the shape of the sliding window；
Weighted filtering equipment is connect with the Objective extraction equipment and the window shaping device respectively, for being directed to the height
The color component value for being worth each of image pixel executes following weighted filtering movement: being determined based on the sliding window
Each pixel nearby of each of high value image pixel, obtains each color point of each pixel nearby
Magnitude is weighted filtering processing to each color component value of each pixel nearby to obtain the high value image
Each of pixel amendment color component value；
Output equipment is filtered, is connect with the weighted filtering equipment, for based on each of high value image pixel
The amendment color component value of point obtains and exports amendment image；
Performer's identification apparatus is connect with the filtering output equipment, for receiving the amendment image, is based on preset reference human body
Pattern identifies from the amendment image and is partitioned into each performer's subgraph；
Grade acquires equipment, selects equipment and performer's identification apparatus to connect with described dub in background music respectively, described each for receiving
A performer's subgraph carries out posture detection to each performer's subgraph to determine corresponding movement rank, to each performer's
The corresponding each movement rank of image carries out mean value computation to obtain the movement of the film of the live buffer memory device caching
Rank.
2. movie contents matching mechanism for seedlings as described in claim 1, it is characterised in that:
The weighted filtering equipment is weighted filtering processing to each color component value of each pixel nearby to obtain
It includes: every in the high value image for obtaining the amendment color component value of each of high value image pixel
Pixel near one pixel is closer, it is bigger that color component value participates in weighted value used in weighted filtering processing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810860054.3A CN109309863B (en) | 2018-08-01 | 2018-08-01 | Movie contents matching mechanism for seedlings |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810860054.3A CN109309863B (en) | 2018-08-01 | 2018-08-01 | Movie contents matching mechanism for seedlings |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109309863A CN109309863A (en) | 2019-02-05 |
| CN109309863B true CN109309863B (en) | 2019-09-13 |
Family
ID=65226064
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810860054.3A Active CN109309863B (en) | 2018-08-01 | 2018-08-01 | Movie contents matching mechanism for seedlings |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109309863B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109876473B (en) * | 2018-08-02 | 2020-07-21 | 莱芜职业技术学院 | Computer-aided application platform |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102103877A (en) * | 2009-12-22 | 2011-06-22 | 索尼公司 | Image/video data editing apparatus and method for editing image/video data |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1666967B1 (en) * | 2004-12-03 | 2013-05-08 | Magix AG | System and method of creating an emotional controlled soundtrack |
| CN101727943B (en) * | 2009-12-03 | 2012-10-17 | 无锡中星微电子有限公司 | Method and device for dubbing music in image and image display device |
| CN102256030A (en) * | 2010-05-20 | 2011-11-23 | Tcl集团股份有限公司 | Photo album showing system capable of matching background music and background matching method thereof |
| CN106503034B (en) * | 2016-09-14 | 2019-07-19 | 厦门黑镜科技有限公司 | A kind of method and device for motion picture soundtrack |
| CN108268530B (en) * | 2016-12-30 | 2022-04-29 | 阿里巴巴集团控股有限公司 | Lyric score generation method and related device |
-
2018
- 2018-08-01 CN CN201810860054.3A patent/CN109309863B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102103877A (en) * | 2009-12-22 | 2011-06-22 | 索尼公司 | Image/video data editing apparatus and method for editing image/video data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109309863A (en) | 2019-02-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110418208B (en) | Subtitle determining method and device based on artificial intelligence | |
| US10692480B2 (en) | System and method of reading environment sound enhancement based on image processing and semantic analysis | |
| CN106504304B (en) | A kind of method and device of animation compound | |
| TWI681317B (en) | Human-computer interaction method and human-computer interaction system | |
| US10460732B2 (en) | System and method to insert visual subtitles in videos | |
| CN109951654A (en) | A kind of method of Video Composition, the method for model training and relevant apparatus | |
| SG173496A1 (en) | Method and system for rendering an entertainment animation | |
| CN106251390B (en) | Animation editing method and moving image editing apparatus | |
| CN110322760B (en) | Voice data generation method, device, terminal and storage medium | |
| KR20160012902A (en) | Method and device for playing advertisements based on associated information between audiences | |
| JP2011217197A (en) | Electronic apparatus, reproduction control system, reproduction control method, and program thereof | |
| WO2014194488A1 (en) | Karaoke avatar animation based on facial motion data | |
| WO2022179453A1 (en) | Sound recording method and related device | |
| CN108200334A (en) | Image capturing method, device, storage medium and electronic equipment | |
| CN108093167A (en) | Use the operable camera of natural language instructions | |
| CN111225237B (en) | Sound and picture matching method of video, related device and storage medium | |
| KR20120038616A (en) | Method and system for providing marker-less immersive augmented reality | |
| CN109309863B (en) | Movie contents matching mechanism for seedlings | |
| JP6268287B2 (en) | Moving image generating apparatus, moving image generating method, and program | |
| JP2012108923A (en) | Composite image output device and composite image output processing program | |
| CN109672927A (en) | Movie contents matching process | |
| CN108095465A (en) | A kind of image processing method and device | |
| Kendall | Visualization by ear: Auditory imagery for scientific visualization and virtual reality | |
| CN115633223A (en) | Video processing method and device, electronic equipment and storage medium | |
| JP2015176592A (en) | Animation generation device, animation generation method, and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20190808 Address after: 322300 Beech Creek Village, Panfeng Township, Pan'an County, Jinhua City, Zhejiang Province Applicant after: Pan'an Guiguzi Cultural Planning Co., Ltd. Address before: 223003 No. 11 Meicheng East Road, Huai'an Development Zone, Jiangsu Province Applicant before: Li Chunlian |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20211008 Address after: 518101 building 6a, Qianhai enterprise residence, No. 63, Qianwan 1st Road, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong Patentee after: Shenzhen laowantong Network Co.,Ltd. Address before: 322300 Pan Feng Xiang Ju Xi Cun, Pan'an County, Jinhua City, Zhejiang Province Patentee before: Pan'an Guiguzi Cultural Planning Co.,Ltd. |