CN108965741A - Run-out describing love affairs scale designation platform - Google Patents
Run-out describing love affairs scale designation platform Download PDFInfo
- Publication number
- CN108965741A CN108965741A CN201810850890.3A CN201810850890A CN108965741A CN 108965741 A CN108965741 A CN 108965741A CN 201810850890 A CN201810850890 A CN 201810850890A CN 108965741 A CN108965741 A CN 108965741A
- Authority
- CN
- China
- Prior art keywords
- run
- pixel
- image
- equipment
- value
- 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
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of run-out describing love affairs scale designation platforms, comprising: label equipment for customizing is the corresponding describing love affairs scale label of video data customization to post-processing for receiving run-out describing love affairs degree, and based on the run-out describing love affairs degree；Nonlinear editing technology under the operation of editorial staff, realizes the non-linear editing for treating the video data of post-processing for receiving the video data to post-processing；Video intercepting equipment, for receiving the video data to post-processing, multiple run-out images are extracted from the video data to post-processing, wherein multiple timestamps of multiple run-out images of the extraction of the video intercepting equipment keep equidistant time interval；User input equipment is connect with the video intercepting equipment, the equidistant time interval between multiple timestamps of multiple run-out images of the extraction for setting the video intercepting equipment.By means of the invention it is possible to provide valuable reference data for non-linear editing.
Description
Technical field
The present invention relates to non-linear editing field more particularly to a kind of run-out describing love affairs scale designation platforms.
Background technique
Piece caudal flexure also known as: finale.Acute end occurs in TV play, tv animation, and number can be more than a first song sometimes.Subsequent
It can be indicated in the primary sound CD and animation information of distribution with ED1, ED2 or piece caudal flexure one, piece caudal flexure are second-class.The number of piece caudal flexure
It is usually more than Presence of the Moment.
The run-out joint performance of quyi of film is up to five minutes or more, and TV play is in four minutes or so, and animation is generally in one point of half.
Summary of the invention
In order to solve in the prior art video image describing love affairs degree can not real-time detection the technical issues of, the present invention provides one
Kind run-out describing love affairs scale designation platform.
Wherein, the present invention at least has following three important inventive points:
(1) during carrying out non-linear editing to video, human body tightness degree in video image is identified, to obtain phase
The run-out describing love affairs degree answered, and be that the video stamps customization label for video management side and spectators based on the run-out describing love affairs degree
With reference to；
(2) using two-stage confirmation by the way of to salt-pepper noise point carry out high-precision detection, wherein by gray value be 0 or 255
Pixel be determined as spiced salt initial survey pixel, following processing is executed to each spiced salt initial survey pixel: being determined each around it
Each vicinity points in each direction in a direction determine its gray value and each vicinity points in each direction
The absolute value of gray value mean value will choose the smallest absolute value of numerical value as reference value, when described in the absolute value of all directions
When reference value is greater than preset difference value threshold value, spiced salt confirmation pixel is determined that it is；
(3) only salt-pepper noise is filtered, particular, it is important that the picture based on all directions around salt-pepper noise
The grey value profile situation of vegetarian refreshments selects different filter patterns, further improves salt-pepper noise filter effect.
According to an aspect of the present invention, a kind of run-out describing love affairs scale designation platform is provided, the platform includes:
Label equipment for customizing is the view to post-processing for receiving run-out describing love affairs degree, and based on the run-out describing love affairs degree
The corresponding describing love affairs scale label of frequency data customization；Nonlinear editing technology is being edited for receiving the video data to post-processing
Under the operation of personnel, the non-linear editing for treating the video data of post-processing is realized；Video intercepting equipment, for receiving after
The video data of phase processing, extracts multiple run-out images, wherein the video from the video data to post-processing
The multiple timestamps for intercepting multiple run-out images of the extraction of equipment keep equidistant time interval；User input equipment, with institute
State the connection of video intercepting equipment, multiple timestamps of multiple run-out images of the extraction for setting the video intercepting equipment it
Between equidistant time interval；First analytical equipment is connect with the video intercepting equipment, for receiving the multiple run-out figure
Picture identifies the scene of each run-out image, will there is the run-out image for repeating scene to divide one group into, to obtain multiple groups run-out figure
Picture, it is right respectively to export multiple groups run-out image using the minimum image of redundancy in each group of run-out image as low redundant image
The multiple low redundant images answered；Gray scale extract equipment is connect with first analytical equipment, for receiving the low redundancy figure
Picture extracts respective gray value to each of low redundant image pixel, and exports each in the low redundant image
Each gray value of a pixel；First detection device is connect with the gray scale extract equipment, for receiving the low redundancy figure
Each gray value of each pixel as in, and the pixel that gray value is 0 or 255 is determined as spiced salt initial survey pixel, and
Export each spiced salt initial survey pixel in the low redundant image；Second detection device is connect with first detection device,
For receiving each spiced salt initial survey pixel in the low redundant image, following place is executed to each spiced salt initial survey pixel
Reason: determining each vicinity points in each direction in all directions around it, determines its gray value and each direction
The absolute value of the gray value mean value of each vicinity points will be chosen the smallest absolute value of numerical value and be made in the absolute value of all directions
Spiced salt confirmation pixel is determined that it is when the reference value is greater than preset difference value threshold value for reference value；Second detection is set
The standby each spiced salt confirmation pixel being also used to export in the low redundant image；Mode selection device, respectively with the gray scale
Extract equipment is connected with second detection device, for receiving the confirmation pixel of each spiced salt in the low redundant image,
Following processing is executed to each spiced salt confirmation pixel: using initial filter window for it, judges in the low redundant image
The quantity of spiced salt confirmation pixel in initial filter window centered on it, when the quantity transfinites, by initial filter
The length of window continues the judgement of the confirmation pixel quantity of the spiced salt in filter window plus 2 pixels, until filtering
Spiced salt confirmation pixel quantity in window does not transfinite, using filter window at this time as final filter window, based on described in most
Whole filter window is weighted mean filter processing to it, to obtain its corresponding filtering gray value；It is set in the model selection
In standby, the gray value of the non-spiced salt confirmation pixel in the low redundant image is exported directly as filtering gray value；Second
Analytical equipment is connect with the mode selection device, for receiving each filtered image, based on standardized human body's profile from every
Each human object is obtained in one filtered image, each filtering figure is determined based on the mutual alignment of each human object
Human body tightness degree as in；Third analytical equipment is connect with second analytical equipment, for receiving each filtering figure
Human body tightness degree as in, and mean value computation is carried out to each human body tightness degree in each filtered image, to obtain
Corresponding run-out describing love affairs degree.
More specifically, in the run-out describing love affairs scale designation platform: in second analytical equipment, being based on standardized human body
It includes: by each filtered image and the standardized human body that profile obtains each human object from each filtered image
Outline is to obtain each human object in each filtered image.
More specifically, in the run-out describing love affairs scale designation platform: the mode selection device is also used to based on described low
Each filtering gray value of each pixel is determining in redundant image and exports and corresponding with the low redundant image has filtered figure
Picture.
More specifically, in the run-out describing love affairs scale designation platform: in second detection device, by the low redundancy
The pixel that spiced salt confirmation pixel is not belonging in image is all set to non-spiced salt confirmation pixel.
More specifically, in the run-out describing love affairs scale designation platform: being 0 by gray value in first detection device
Pixel be determined as green pepper initial survey pixel.
More specifically, in the run-out describing love affairs scale designation platform: in first detection device, being by gray value
255 pixel is determined as salt initial survey pixel.
More specifically, in the run-out describing love affairs scale designation platform: the label equipment for customizing, the non-linear editing are set
Standby, the described video intercepting equipment and first analytical equipment are integrated on same integrated circuit board.
More specifically, in the run-out describing love affairs scale designation platform: in the third analytical equipment, having been filtered to each
The result that each human body tightness degree in image carries out mean value computation acquisition is higher, and corresponding run-out describing love affairs degree is higher.
Detailed description of the invention
Embodiment of the present invention is described below with reference to attached drawing, in which:
Fig. 1 is the external mould according to the third analytical equipment of the run-out describing love affairs scale designation platform shown in embodiment of the present invention
Block interface schema.
Specific embodiment
The embodiment of run-out describing love affairs scale designation platform of the invention is described in detail below with reference to accompanying drawings.
The information often indicated in piece caudal flexure have performer or voice-over actor, playwright, screenwriter or script, TV play operating back-stage personnel or
Animation original painting and cartoon making personnel, associated companies member, the mechanism that expresses one's thanks to or personage, piece caudal flexure ci and qu singer etc..These are
The case where common practice has a different situations according to works, piece caudal flexure just changes song after also will use a season to two seasons as head
It is bent.
In order to overcome above-mentioned deficiency, the present invention has built a kind of run-out describing love affairs scale designation platform, can effectively solve the problem that corresponding
The technical issues of.
Fig. 1 is the external mould according to the third analytical equipment of the run-out describing love affairs scale designation platform shown in embodiment of the present invention
Block interface schema.
The run-out describing love affairs scale designation platform shown according to an embodiment of the present invention includes:
Label equipment for customizing is the view to post-processing for receiving run-out describing love affairs degree, and based on the run-out describing love affairs degree
The corresponding describing love affairs scale label of frequency data customization；
Nonlinear editing technology, for receiving the video data to post-processing, under the operation of editorial staff, realization pair
The non-linear editing of video data to post-processing；
Video intercepting equipment, for receiving the video data to post-processing, from the video data to post-processing
In extract multiple run-out images, wherein multiple timestamps of multiple run-out images of the extraction of the video intercepting equipment are protected
Hold equidistant time interval；
User input equipment connect with the video intercepting equipment, for setting the extraction of the video intercepting equipment
Equidistant time interval between multiple timestamps of multiple run-out images；
First analytical equipment is connect with the video intercepting equipment, for receiving the multiple run-out image, is identified each
The scene of a run-out image will there is the run-out image for repeating scene to divide one group into, to obtain multiple groups run-out image, by each group
The minimum image of redundancy is corresponding multiple low superfluous to export multiple groups run-out image as low redundant image in run-out image
Remaining image；
Gray scale extract equipment is connect with first analytical equipment, for receiving the low redundant image, to described low superfluous
Each of remaining image pixel extracts respective gray value, and exports each of each pixel in the low redundant image
Gray value；
First detection device is connect with the gray scale extract equipment, for receiving each pixel in the low redundant image
Each gray value of point, and the pixel that gray value is 0 or 255 is determined as spiced salt initial survey pixel, and export described low superfluous
Each spiced salt initial survey pixel in remaining image；
Second detection device is connect with first detection device, for receiving each green pepper in the low redundant image
Salt initial survey pixel executes following processing to each spiced salt initial survey pixel: determining around it each side in all directions
To each vicinity points, determine the absolute of its gray value and the gray value mean value of each vicinity points in each direction
Value will choose the smallest absolute value of numerical value as reference value, when the reference value is poor greater than default in the absolute value of all directions
When being worth threshold value, spiced salt confirmation pixel is determined that it is；Second detection device is also used to export in the low redundant image
Each spiced salt confirms pixel；
Mode selection device is connect, for receiving respectively with the gray scale extract equipment and second detection device
Each spiced salt confirmation pixel in low redundant image is stated, following processing is executed to each spiced salt confirmation pixel: being made for it
With initial filter window, the spiced salt confirmation pixel in the initial filter window in the low redundant image centered on it is judged
Quantity the length of initial filter window is continued in filter window plus 2 pixels when the quantity transfinites
The spiced salt confirms the judgement of pixel quantity, until the spiced salt confirmation pixel quantity in filter window does not transfinite, by filter at this time
Wave window is weighted mean filter processing to it as final filter window, based on the final filter window, to obtain it
Corresponding filtering gray value；In the mode selection device, to the non-spiced salt confirmation pixel in the low redundant image
Gray value is directly as filtering gray value output；
Second analytical equipment is connect with the mode selection device, for receiving each filtered image, is based on standard
Human body contour outline obtains each human object from each filtered image, is determined often based on the mutual alignment of each human object
Human body tightness degree in one filtered image；
Third analytical equipment is connect, for receiving the human body in each filtered image with second analytical equipment
Tightness degree, and mean value computation is carried out to each human body tightness degree in each filtered image, to obtain corresponding run-out
Describing love affairs degree.
Then, continue that the specific structure of run-out describing love affairs scale designation platform of the invention is further detailed.
In the run-out describing love affairs scale designation platform: in second analytical equipment, based on standardized human body's profile from every
It includes: by each filtered image and standardized human body's outline that each human object is obtained in one filtered image
To obtain each human object in each filtered image.
In the run-out describing love affairs scale designation platform: the mode selection device is also used to based in the low redundant image
Each filtering gray value of each pixel is determining and exports filtered image corresponding with the low redundant image.
In the run-out describing love affairs scale designation platform: in second detection device, by the low redundant image not
The pixel for belonging to spiced salt confirmation pixel is all set to non-spiced salt confirmation pixel.
In the run-out describing love affairs scale designation platform: in first detection device, the pixel for being 0 by gray value is true
It is set to green pepper initial survey pixel.
In the run-out describing love affairs scale designation platform: in first detection device, the pixel for being 255 by gray value
It is determined as salt initial survey pixel.
In the run-out describing love affairs scale designation platform: the label equipment for customizing, the nonlinear editing technology, the view
Frequency interception equipment and first analytical equipment are integrated on same integrated circuit board.
In the run-out describing love affairs scale designation platform: in the third analytical equipment, in each filtered image
The result that each human body tightness degree carries out mean value computation acquisition is higher, and corresponding run-out describing love affairs degree is higher.
In addition, difference is respectively adopted in first analytical equipment, second analytical equipment and the third analytical equipment
The SOC chip of model is realized.System on Chip, abbreviation SOC namely system on chip.It is said from narrow sense angle, he is information
The integrated chip of the system core is that system core component is integrated on one chip；It is said from broadest scope, SOC is one micro-
Mini-system, if central processing unit (CPU) is brain, then SOC is exactly the system for including brain, heart, eyes and hand.
Domestic and international academia, which generally be inclined to, is defined as SOC by microprocessor, Analog IP core, number IP kernel and memory (or piece external memory
Store up control interface) it integrates on a single chip, he is usually customization, or the standardized product towards special-purpose.
The basic content that SOC is defined is mainly both ways: one is his composition, the second is his forming process.It is system-level
The composition of chip can be system level chip control logic module, microprocessor/microcontroller CPU core module, digital signal
Processor DSP module, the memory module of insertion and the external interface module communicated, the AFE(analog front end) containing ADC/DAC
Module, power supply provides and power managed module.
Using run-out describing love affairs scale designation platform of the invention, can not be examined in real time for video image describing love affairs degree in the prior art
The technical issues of survey, identifies human body tightness degree in video image during carrying out non-linear editing to video, to obtain
Corresponding run-out describing love affairs degree, and be that the video stamps customization label for video management side and sight based on the run-out describing love affairs degree
Crowd's reference；High-precision detection is carried out to salt-pepper noise point by the way of two-stage confirmation, wherein the picture for being 0 or 255 by gray value
Vegetarian refreshments is determined as spiced salt initial survey pixel, executes following processing to each spiced salt initial survey pixel: determining each side around it
Each vicinity points in each direction in determine the gray scale of its gray value and each vicinity points in each direction
It is worth the absolute value of mean value, the smallest absolute value of numerical value will be chosen in the absolute value of all directions as reference value, when the reference
When value is greater than preset difference value threshold value, spiced salt confirmation pixel is determined that it is；Only salt-pepper noise is filtered, it is particularly important
, the grey value profile situation based on the pixel of all directions around salt-pepper noise selects different filter patterns, into one
Step improves salt-pepper noise filter effect.
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 run-out describing love affairs scale designation platform, which is characterized in that the platform includes:
Label equipment for customizing is the video counts to post-processing for receiving run-out describing love affairs degree, and based on the run-out describing love affairs degree
According to the corresponding describing love affairs scale label of customization；
Nonlinear editing technology, for receiving the video data to post-processing, under the operation of editorial staff, after realization is treated
The non-linear editing of the video data of phase processing；
Video intercepting equipment is mentioned from the video data to post-processing for receiving the video data to post-processing
Take out multiple run-out images, wherein multiple timestamps holding of multiple run-out images of the extraction of the video intercepting equipment etc.
Time interval interval；
User input equipment is connect with the video intercepting equipment, for set the video intercepting equipment extraction it is multiple
Equidistant time interval between multiple timestamps of run-out image；
First analytical equipment is connect with the video intercepting equipment, for receiving the multiple run-out image, identifies each piece
The scene of tail image will there is the run-out image for repeating scene to divide one group into, to obtain multiple groups run-out image, by each group of run-out
The minimum image of redundancy is as low redundant image in image, to export the corresponding multiple low redundancy figures of multiple groups run-out image
Picture；
Gray scale extract equipment is connect with first analytical equipment, for receiving the low redundant image, to the low redundancy figure
Each of picture pixel extracts respective gray value, and exports each gray scale of each pixel in the low redundant image
Value；
First detection device is connect with the gray scale extract equipment, for receiving each pixel in the low redundant image
Each gray value, and the pixel that gray value is 0 or 255 is determined as spiced salt initial survey pixel, and export the low redundancy figure
Each spiced salt initial survey pixel as in；
Second detection device is connect with first detection device, at the beginning of receiving each spiced salt in the low redundant image
Pixel is examined, following processing is executed to each spiced salt initial survey pixel: determining around it each direction in all directions
Each vicinity points determine the absolute value of the gray value mean value of its gray value and each vicinity points in each direction,
The smallest absolute value of numerical value will be chosen in the absolute value of all directions as reference value, when the reference value is greater than preset difference value threshold
When value, spiced salt confirmation pixel is determined that it is；Second detection device is also used to export each in the low redundant image
The spiced salt confirms pixel；
Mode selection device is connect with the gray scale extract equipment and second detection device respectively, described low for receiving
Each spiced salt in redundant image confirms pixel, executes following processing to each spiced salt confirmation pixel: using just for it
Beginning filter window judges the number of the spiced salt confirmation pixel in the initial filter window in the low redundant image centered on it
The length of initial filter window is continued the spiced salt in filter window plus 2 pixels when the quantity transfinites by amount
The judgement for confirming pixel quantity, until the spiced salt confirmation pixel quantity in filter window does not transfinite, by spectral window at this time
Mouth is used as final filter window, mean filter processing is weighted to it based on the final filter window, to obtain its correspondence
Filtering gray value；In the mode selection device, to the gray scale of the non-spiced salt confirmation pixel in the low redundant image
Value is directly as filtering gray value output；
Second analytical equipment is connect with the mode selection device, for receiving each filtered image, is based on standardized human body
Profile obtains each human object from each filtered image, determines each based on the mutual alignment of each human object
Human body tightness degree in filtered image；
Third analytical equipment is connect with second analytical equipment, close for receiving the human body in each filtered image
Degree, and mean value computation is carried out to each human body tightness degree in each filtered image, to obtain corresponding run-out describing love affairs
Degree.
2. run-out describing love affairs scale designation platform as described in claim 1, it is characterised in that:
In second analytical equipment, each human object is obtained from each filtered image based on standardized human body's profile
It include: by each filtered image and standardized human body's outline to obtain each individual in each filtered image
Body object.
3. run-out describing love affairs scale designation platform as claimed in claim 2, it is characterised in that:
The mode selection device is also used to determine based on each filtering gray value of each pixel in the low redundant image
And export filtered image corresponding with the low redundant image.
4. run-out describing love affairs scale designation platform as claimed in claim 3, it is characterised in that:
In second detection device, the pixel that spiced salt confirmation pixel is not belonging in the low redundant image is all set to
The non-spiced salt confirms pixel.
5. run-out describing love affairs scale designation platform as claimed in claim 4, it is characterised in that:
In first detection device, the pixel that gray value is 0 is determined as green pepper initial survey pixel.
6. run-out describing love affairs scale designation platform as claimed in claim 5, it is characterised in that:
In first detection device, the pixel that gray value is 255 is determined as salt initial survey pixel.
7. run-out describing love affairs scale designation platform as claimed in claim 6, it is characterised in that:
The label equipment for customizing, the nonlinear editing technology, the video intercepting equipment and the first analytical equipment quilt
It is integrated on same integrated circuit board.
8. run-out describing love affairs scale designation platform as claimed in claim 7, it is characterised in that:
In the third analytical equipment, mean value computation acquisition is carried out to each human body tightness degree in each filtered image
Result it is higher, corresponding run-out describing love affairs degree is higher.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810850890.3A CN108965741A (en) | 2018-07-29 | 2018-07-29 | Run-out describing love affairs scale designation platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810850890.3A CN108965741A (en) | 2018-07-29 | 2018-07-29 | Run-out describing love affairs scale designation platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108965741A true CN108965741A (en) | 2018-12-07 |
Family
ID=64466090
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810850890.3A Pending CN108965741A (en) | 2018-07-29 | 2018-07-29 | Run-out describing love affairs scale designation platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108965741A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101094312A (en) * | 2006-06-20 | 2007-12-26 | 西北工业大学 | Self-adapting method for filtering image with edge being retained |
| CN102479383A (en) * | 2010-11-30 | 2012-05-30 | 上海银晨智能识别科技有限公司 | Method and device for removing salt and pepper noise |
| CN102930553A (en) * | 2011-08-10 | 2013-02-13 | 中国移动通信集团上海有限公司 | Method and device for identifying objectionable video content |
| CN104899842A (en) * | 2015-06-29 | 2015-09-09 | 济南大学 | Ranked-order adaptively extremum median filtering method for remote line structured light image |
| CN105005777A (en) * | 2015-07-30 | 2015-10-28 | 科大讯飞股份有限公司 | Face-based audio and video recommendation method and face-based audio and video recommendation system |
| CN105183758A (en) * | 2015-07-22 | 2015-12-23 | 深圳市万姓宗祠网络科技股份有限公司 | Content recognition method for continuously recorded video or image |
-
2018
- 2018-07-29 CN CN201810850890.3A patent/CN108965741A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101094312A (en) * | 2006-06-20 | 2007-12-26 | 西北工业大学 | Self-adapting method for filtering image with edge being retained |
| CN102479383A (en) * | 2010-11-30 | 2012-05-30 | 上海银晨智能识别科技有限公司 | Method and device for removing salt and pepper noise |
| CN102930553A (en) * | 2011-08-10 | 2013-02-13 | 中国移动通信集团上海有限公司 | Method and device for identifying objectionable video content |
| CN104899842A (en) * | 2015-06-29 | 2015-09-09 | 济南大学 | Ranked-order adaptively extremum median filtering method for remote line structured light image |
| CN105183758A (en) * | 2015-07-22 | 2015-12-23 | 深圳市万姓宗祠网络科技股份有限公司 | Content recognition method for continuously recorded video or image |
| CN105005777A (en) * | 2015-07-30 | 2015-10-28 | 科大讯飞股份有限公司 | Face-based audio and video recommendation method and face-based audio and video recommendation system |
Non-Patent Citations (2)
| Title |
|---|
| 何东健: "《数字图像处理》", 28 February 2015 * |
| 罗庆生等: "《仿生四足机器人技术》", 30 April 2016 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tremeau et al. | Color in image and video processing: most recent trends and future research directions | |
| US9456131B2 (en) | Video processing systems and methods | |
| RU2727101C1 (en) | Image processing device, method and storage medium | |
| CN110914873B (en) | Augmented reality method, device, mixed reality glasses and storage medium | |
| CN108447017A (en) | Face virtual face-lifting method and device | |
| CN104540275B (en) | A kind of method for adjusting live lighting device, equipment and system | |
| US20140300758A1 (en) | Video processing systems and methods | |
| KR102335899B1 (en) | Systems, methods, apparatuses, and computer-readable storage media for collecting color information about an object undergoing a 3d scan | |
| CN108701359A (en) | Across the video frame tracking interest region with corresponding depth map | |
| CN106258010A (en) | 2D image dissector | |
| EP1405272A1 (en) | Method and apparatus for interleaving a user image in an original image | |
| CN109068058A (en) | Filming control method, device and electronic equipment under super night scene mode | |
| CN110378944A (en) | Depth map processing method, device and electronic equipment | |
| CN108604369A (en) | A kind of method, apparatus, equipment and the convolutional neural networks of removal picture noise | |
| CN109803096A (en) | A kind of display methods and system based on pulse signal | |
| CN114419702B (en) | Digital person generation model, training method of model, and digital person generation method | |
| CN108022207A (en) | Image processing method, device, storage medium and electronic equipment | |
| CN109241956A (en) | Method, apparatus, terminal and the storage medium of composograph | |
| CN108961195A (en) | Image processing method and device, image collecting device, readable storage medium storing program for executing and computer equipment | |
| KR20240089729A (en) | Image processing methods, devices, storage media and electronic devices | |
| CN107392883A (en) | The method and system that video display dramatic conflicts degree calculates | |
| CN109587466A (en) | The method and apparatus of colored shadow correction | |
| CN110276831A (en) | Constructing method and device, equipment, the computer readable storage medium of threedimensional model | |
| CN109903265A (en) | A kind of image change area detecting threshold value setting method, system and its electronic device | |
| CN108965741A (en) | Run-out describing love affairs scale designation platform |
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: 20181207 |
|
| RJ01 | Rejection of invention patent application after publication |