CN104469179B - A kind of method being attached to dynamic picture in mobile video - Google Patents
A kind of method being attached to dynamic picture in mobile video Download PDFInfo
- Publication number
- CN104469179B CN104469179B CN201410803625.1A CN201410803625A CN104469179B CN 104469179 B CN104469179 B CN 104469179B CN 201410803625 A CN201410803625 A CN 201410803625A CN 104469179 B CN104469179 B CN 104469179B
- Authority
- CN
- China
- Prior art keywords
- dynamic picture
- picture
- video
- face
- dynamic
- 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.)
- Expired - Fee Related
Links
Landscapes
- Processing Or Creating Images (AREA)
- Studio Circuits (AREA)
Abstract
The invention discloses a kind of method being attached to dynamic picture in mobile video, comprise the following steps：Video and the dynamic picture that is made up of some png sequence frames pictures are obtained, dynamic picture, which is divided into, face tracking, editable word and can not follow the trail of face and editor's class of word three；Face datection is carried out to the whole frame pictures for obtaining video；Some dynamic picture is selected, face judgement is carried out to the present frame picture of video；Whether there is the display of the type progress dynamic picture of face and dynamic picture according to previous frame picture.The present invention adds dynamic picture after video completes to shoot, and this rearmounted addition dynamic picture method can accomplish free adjustment addition dynamic picture into any picture, while not adding the limitation of motion picture number；With face tracking technology, addition dynamic picture is set more to facilitate.
Description
Technical field
The present invention relates to face tracking technology, more particularly to a kind of method being attached to dynamic picture in mobile video.
Background technology
At present, known dynamic picture is added or incorporated into processing scheme in mobile video all in shooting the video stage
Shi Tianjia dynamic pictures.Dynamic picture has first been added before shooting, has then been shot, such as section, which is shot, terminates so animation
It will terminate.This addition manner is relatively simple, and with limitation, dynamic picture can not be carried out during video is shot
Corresponding operation, such as rotate and scale dynamic picture, can not freely adjust the duration that dynamic picture is shown.This scheme institute
The addition dynamic picture and the enjoyment of shooting video brought will be substantially reduced.The emergence of smart mobile phone, high-definition camera is recorded
The factor such as convenient drastically increases the demand that user shoots video, and the enjoyment for how increasing video needs us conscientious
Thinking.
The content of the invention
It is an object of the invention to for it is existing addition dynamic picture to mobile phone vision operation scheme deficiency there is provided
A kind of method being attached to dynamic picture in mobile video, dynamic picture is added after video completes to shoot, this rearmounted to add
Plus dynamic picture method can accomplish free adjustment addition dynamic picture into any picture, while not adding motion picture
Several limitations.
The purpose of the present invention is achieved through the following technical solutions：Dynamic picture is attached in mobile video by one kind
Method, comprise the following steps：
（1）The acquisition of video and dynamic picture
The video carries camera by calling mobile phone and shot or by accessing the acquisition of system photograph album；
The dynamic picture is made up of 3-30 png sequence frame pictures, one json allocation lists of each dynamic picture correspondence；
The json allocation lists include following information：The sequence number id of dynamic picture, title n, duration du, type type, display location are sat
Mark and copy editor's information；Wherein, type=0 represents the dynamic picture of editable word, and type=1 represents face tracking Dynamic Graph
Piece, type=2, which are represented, can not follow the trail of the dynamic picture of face and editor's word；
（2）The acquisition of video thumbnails and show：Using AVFoundation frameworks by step（1）The video of acquisition turns
Change frame picture into, divide N sections equally according to frame number, the first pictures of each segmented node as video thumbnail in sequence according to
Secondary arrangement；
（3）To step（1）The video of acquisition is scanned：Using CoreImage CIDetector or use
The whole frame pictures for obtaining video are carried out Face datection by the HaarCascadeClassifier in OpenCV；If detection
Human face characteristic point and coordinate information are then preserved to face, data are not otherwise preserved；
（4）Addition and display of the dynamic picture on video, specifically include following sub-step：
（4.1）Pass through player step display（1）The a certain frame of the video of acquisition；
（4.2）Some dynamic picture is selected, face judgement is carried out to the present frame picture of video；
If face is shown, then call the json allocation lists of the dynamic picture to judge whether type is 1, i.e., whether be people
Face follows the trail of dynamic picture；
If type=1, with reference to step（3）The human face characteristic point and coordinate information of the present frame of the video of acquisition, dynamic
Display location coordinate information in the json allocation lists of picture is calculated, and obtains the people that dynamic picture central point places present frame
Coordinate at face, and be shown on relevant position；
If face is shown but type ≠ 1, or show that dynamic picture is placed in json allocation lists without face
Initial position in the coordinate information of display location；
If type=0, copy editor's information in json allocation lists is called, by text importing on dynamic picture；
（5）The editor of dynamic picture, specifically includes following sub-step：
（5.1）The start picture that adjustment dynamic picture is shown in video：Pass through step（2）The thumbnail selection video of generation
A certain frame picture, dynamic picture will the frame as starting point play dynamic picture acquiescence display duration；
（5.2）Adjust dynamic picture size and the anglec of rotation：Dynamic picture is pulled to be rotated and scaled；
（5.3）Close dynamic picture and complete the addition of dynamic picture：Dynamic picture is closed, then is removed in current picture
The dynamic picture；Complete to newly increase another dynamic picture after the addition of current dynamic picture into video, operating procedure is such as
Step（4）；The information of all dynamic pictures is saved in array according to time point after completing addition；
（6）The synthesis of dynamic picture and video：Using OpenGl ES render video frames into context, circulation step
（5）The middle array for preserving dynamic picture data, if the sometime point in video with the addition of dynamic picture, according at this
Between dynamic picture in the array put data, corresponding motion picture sequence frame is zoomed in and out by matrixing, rotated
Context is rendered into, video is handled per frame, the video after output synthesis dynamic picture.
Further, the step（4）In, when the present frame picture of video has face to show, during and type=1, Dynamic Graph
The display of piece is specially：Four variables are set in the display location coordinate of json allocation lists：X-axis coordinate fx, Y-axis coordinate fy,
Animation width fw and animation height fh；Two of face are as X-axis in connection video present frame picture, vertical connection face face
As Y-axis, the crosspoint of XY axles is used as the origin of coordinates；Origin is set as X=1 to the distance of left/right eye, origin to face away from
From being set as Y=1；The advance picture by dynamic picture and with face is placed on progress pre-selection positioning, such as Fig. 2 in prototype software or PS
It is shown：Dynamic picture is put into the related position acquisition coordinate of face, the center that dynamic picture is calculated after dynamic picture is placed
Point coordinates, dynamic picture corresponds to size that face relevant position showed by the distance according to origin to left/right eye
Multiple and obtain, animation width fw be origin to left/right eye apart from X multiple, animation height fh according to current fw values and give tacit consent to
The ratio of width to height of dynamic picture is obtained.
Further, the step（4）In, as type=0, the display of dynamic picture is specially：In json allocation lists
Variable is set in copy editor's information：Word content ptext, font tfont, word anglec of rotation tangle, text input box
Center point coordinate value（Tleft, ttop）, text input box wide twidth and high theight, color tRGB, the text of word
The time of occurrence point tbegin and end time point tend of word, text importing is carried out according to the data in copy editor's information.
The beneficial effects of the invention are as follows：The present invention adds dynamic picture after video completes to shoot, and this rearmounted addition is dynamic
State picture approach can accomplish free adjustment addition dynamic picture into any picture, and addition dynamic picture has controllability, no
Limited by video is shot, while not adding the limitation of motion picture number；With face tracking technology, make addition Dynamic Graph
Piece more facilitates.
Brief description of the drawings
Fig. 1 is the specific steps flow chart of the present invention；
Fig. 2 is the schematic diagram being pre-positioned to the dynamic picture for following the trail of face.
Embodiment
The present invention is described in further detail below in conjunction with the accompanying drawings.
As shown in figure 1, a kind of method being attached to dynamic picture in mobile video of the present invention, comprises the following steps：
（1）The acquisition of video and dynamic picture
The video of 2-8 seconds durations will be taken in the elaboration of specific implementation step of the present invention for example.Calling mobile phone is carried
Camera shoots video, and minimum shoot 2 seconds at most shoots 8 seconds videos, can also access the video in system photograph album, such as video mistake
It is long then interception 8 seconds in video.
The dynamic picture constitutes continuous animation, each dynamic picture correspondence one by 3-30 png sequence frame pictures
Json allocation lists；The json allocation lists include following information：The sequence number id of dynamic picture, title n, duration du, type
Type, display location coordinate and copy editor's information；Wherein, type=0 represents the dynamic picture of editable word, the generation of type=1
Table face tracking dynamic picture, type=2, which are represented, can not follow the trail of the dynamic picture of face and editor's word.
Json allocation lists are as follows：
{
"pid":1, the sequence id of // dynamic picture
"fid": 1,
"du":1.1, the acquiescence duration that // dynamic picture is shown
"type":1, the type 0 of // dynamic picture is that the dynamic picture 1 of editable word is to follow the trail of face table
The dynamic picture 2 of feelings is common dynamic picture
"x": 320.0,
"y": 320.0,
"w": 400.0,
"h":120.0, // X Y are the default locations in dynamic picture placement video, and W and H are dynamic pictures
Size
"a": 0.0,
"fx": 0.0,
"fy": -0.5,
"fw": 4.55,
"fh":The dynamic picture that 0.0, //fx-fh follow the trail of face needs to get the relevant position for placing face
"n": "haixiu",
"c":9.0, the number of // sequence frame picture
"pText":" Na Ni ", the dynamic picture of // editable word in this way is, it is necessary to fill in ptext to tend data
"tFont":Font in " SentyTEApro ", // text importing video, can be used the network font by authorizing
"tAngle":0.0, // word is placed on the anglec of rotation of dynamic picture
"tLeft":205.0,
"tTop":170.0,
"twidth":210.0,
"tHeight":190.0, //tLeft-tHeight are the center point coordinate and input model for the size that word is inputted
Enclose
"tR":255.0,
"tG":255.0,
"tB":255.0, //RGB are the color of word
"tBegin":0.5,
"tEnd":1.45, //tBegin-tEnd are the display time of word
"frameArry": [
{"time":0.0,"pic":0},
{"time":0.1,"pic":1},
{"time":0.2,"pic":2},
{"time":0.3,"pic":3},
{"time":0.4,"pic":4},
{"time":0.5,"pic":4},
{"time":0.6,"pic":4},
{"time":0.7,"pic":5},
{"time":0.8,"pic":6},
{"time":0.9,"pic":7},
{"time":1.0,"pic":8 } // dynamic picture frame number and frame per second
]
}
（2）The acquisition of video thumbnails and show：Using AVFoundation frameworks by step（1）The video of acquisition turns
Change frame picture into, or image is read from local file using Video Decoder.Wherein video 30 frame per second, is regarded to acquisition
Frequency picture is handled, and is divided equally according to frame number and is taken 8 sections, take each pictures of segmented node first as video thumbnail according to
Order is arranged in order.
（3）To step（1）The video of acquisition is scanned：Using CoreImage CIDetector or use
The whole frame pictures for obtaining video are carried out Face datection by the HaarCascadeClassifier in OpenCV；If detection
Human face characteristic point and coordinate information are then preserved to face, data are not otherwise preserved；
（4）Addition and display of the dynamic picture on video, specifically include following sub-step：
（4.1）Pass through player step display（1）The a certain frame of the video of acquisition；
（4.2）Some dynamic picture is selected, face judgement is carried out to the present frame picture of video；
If face is shown, then call the json allocation lists of the dynamic picture to judge whether type is 1, i.e., whether be people
Face follows the trail of dynamic picture；
If type=1, with reference to step（3）The human face characteristic point and coordinate information of the present frame of the video of acquisition, dynamic
Display location coordinate information in the json allocation lists of picture is calculated, and obtains the people that dynamic picture central point places present frame
Coordinate at face, and be shown on relevant position；The display of dynamic picture is specially：In the display location coordinate of json allocation lists
Four variables of middle setting：X-axis coordinate fx, Y-axis coordinate fy, animation width fw and animation height fh；Connect video present frame picture
Two of middle face are as X-axis, and vertical connection face face is as Y-axis, and the crosspoint of XY axles is used as the origin of coordinates；Origin is arrived
The distance of left/right eye is set as X=1, and the distance of origin to face is set as Y=1；The advance picture by dynamic picture and with face
It is placed on progress pre-selection positioning in prototype software or PS：Dynamic picture is put into the related position acquisition coordinate of face, placed active
Calculate the center point coordinate of dynamic picture after state picture, dynamic picture corresponds to size that face relevant position showed by root
Obtained according to origin to left/right eye apart from multiple, animation width fw is for origin to left/right eye apart from X multiple, animation
Height fh is obtained according to the ratio of width to height of current fw values and acquiescence dynamic picture.This way ensure that different faces add different chis
Very little dynamic picture also will be, and be the dynamic picture size for meeting the shape of face.When face duration is more than dynamic picture in itself
Duration when, only display dynamic picture acquiescence duration；When face duration is less than the duration of dynamic picture in itself, dynamic picture
The duration of display is the duration of face, i.e., face is disappeared, and dynamic picture, which also disappears, not to be shown.
If face is shown but type ≠ 1, or show that dynamic picture is placed in json allocation lists without face
XY values in the coordinate information of display location are initial position；
If type=0, copy editor's information in json allocation lists is called, by text importing on dynamic picture；It is dynamic
The display of state picture is specially：Variable is set in copy editor's information of json allocation lists：Word content ptext, font
Tfont, word anglec of rotation tangle, the center point coordinate value of text input box（Tleft, ttop）, text input box width
Twidth and high theight, the color tRGB of word, the time of occurrence point tbegin of word and end time point tend, according to
Data in copy editor's information carry out text importing.
（5）The editor of dynamic picture, specifically includes following sub-step：
（5.1）The start picture that adjustment dynamic picture is shown in video：Pass through step（2）The thumbnail selection video of generation
A certain frame picture, dynamic picture will the frame as starting point play dynamic picture acquiescence display duration；
（5.2）Adjust dynamic picture size and the anglec of rotation：Dynamic picture is pulled to be rotated and scaled（Dynamic picture can
To be scaled by XY equal proportions in parameter）.
（5.3）Close dynamic picture and complete the addition of dynamic picture：Dynamic picture is closed, then is removed in current picture
The dynamic picture；Complete to newly increase another dynamic picture after the addition of current dynamic picture into video, operating procedure is such as
Step（4）；The information of all dynamic pictures is saved in array according to time point after completing addition；
（6）The synthesis of dynamic picture and video：Using OpenGl ES render video frames into context, circulation step
（5）The middle array for preserving dynamic picture data, if the sometime point in video with the addition of dynamic picture, according at this
Between dynamic picture in the array put data, corresponding motion picture sequence frame is zoomed in and out by matrixing, rotated
Context is rendered into, video is handled per frame, the video after output synthesis dynamic picture.
Description of the invention is provided for the sake of example and description, is not exhaustively or by the present invention to limit
In disclosed form.Many algorithms and implementation are obvious for the ordinary skill in the art.Selection and
It, in order to more preferably illustrate the principle and practical application of the present invention, and is that one of ordinary skill in the art can that description embodiment, which is,
Understand the present invention to design the various embodiments with various modifications suitable for special-purpose.
Claims (3)
1. a kind of method being attached to dynamic picture in mobile video, it is characterised in that comprise the following steps：
（1）The acquisition of video and dynamic picture
The video carries camera by calling mobile phone and shot or by accessing the acquisition of system photograph album；
The dynamic picture is made up of 3-30 png sequence frame pictures, one json allocation lists of each dynamic picture correspondence；It is described
Json allocation lists include following information：The sequence number id of dynamic picture, title n, duration du, type type, display location coordinate and
Copy editor's information；Wherein, type=0 represents the dynamic picture of editable word, and type=1 represents face tracking dynamic picture,
Type=2, which are represented, can not follow the trail of the dynamic picture of face and editor's word；
（2）The acquisition of video thumbnails and show：Using AVFoundation frameworks by step（1）The Video Quality Metric of acquisition into
Frame picture, divides N sections equally, the first pictures of each segmented node are arranged successively in sequence as the thumbnail of video according to frame number
Row；
（3）To step（1）The video of acquisition is scanned：Using CoreImage CIDetector or use OpenCV
In HaarCascadeClassifier, to obtain video whole frame pictures carry out Face datection；If detecting face
Human face characteristic point and coordinate information are then preserved, data are not otherwise preserved；
（4）Addition and display of the dynamic picture on video, specifically include following sub-step：
（4-1）Pass through player step display（1）The a certain frame of the video of acquisition；
（4-2）Some dynamic picture is selected, face judgement is carried out to the present frame picture of video；
If face is shown, then call the json allocation lists of the dynamic picture to judge whether type is 1, i.e., whether be that face is chased after
Track dynamic picture；
If type=1, with reference to step（3）Human face characteristic point and coordinate information, the dynamic picture of the present frame of the video of acquisition
Json allocation lists in display location coordinate information calculated, obtain dynamic picture central point place present frame face at
Coordinate, and be shown on relevant position；
If face is shown but type ≠ 1, or shown without face, dynamic picture is placed in json allocation lists and shown
Initial position in location coordinate information；
If type=0, copy editor's information in json allocation lists is called, by text importing on dynamic picture；
（5）The editor of dynamic picture, specifically includes following sub-step：
（5-1）The start picture that adjustment dynamic picture is shown in video：Pass through step（2）Certain of the thumbnail selection video of generation
One frame picture, dynamic picture will play the display duration that dynamic picture is given tacit consent in the frame as starting point；
（5-2）Adjust dynamic picture size and the anglec of rotation：Dynamic picture is pulled to be rotated and scaled；
（5-3）Close dynamic picture and complete the addition of dynamic picture：Dynamic picture is closed, then removes this in current picture and moves
State picture；Complete to newly increase another dynamic picture after the addition of current dynamic picture into video, operating procedure such as step
（4）；The information of all dynamic pictures is saved in array according to time point after completing addition；
（6）The synthesis of dynamic picture and video：Using OpenGl ES render video frames into context, circulation step（5）In
The array of dynamic picture data is preserved, if the sometime point in video with the addition of dynamic picture, according at the time point
Array in dynamic picture data, corresponding motion picture sequence frame is zoomed in and out by matrixing, rotated rendering
To context, video is handled per frame, the video after output synthesis dynamic picture.
2. a kind of method being attached to dynamic picture in mobile video according to claim 1, it is characterised in that the step
Suddenly（4）In, when the present frame picture of video has face to show, during and type=1, the display of dynamic picture is specially：Match somebody with somebody in json
Put four variables of setting in the display location coordinate of table：X-axis coordinate fx, Y-axis coordinate fy, animation width fw and animation height fh；
Two of face are as X-axis in connection video present frame picture, and vertical connection face face is used as Y-axis, and the crosspoint of XY axles is made
For the origin of coordinates；Origin is set as X=1 to the distance of left/right eye, and the distance of origin to face is set as Y=1；In advance will dynamic
Picture and the picture progress pre-selection positioning with face：Dynamic picture is put into the related position acquisition coordinate of face, placed active
Calculate the center point coordinate of dynamic picture after state picture, dynamic picture corresponds to size that face relevant position showed by root
Obtained according to origin to left/right eye apart from multiple, animation width fw is for origin to left/right eye apart from X multiple, animation
Height fh is obtained according to the ratio of width to height of current fw values and acquiescence dynamic picture.
3. a kind of method being attached to dynamic picture in mobile video according to claim 1, it is characterised in that the step
Suddenly（4）In, as type=0, the display of dynamic picture is specially：Variable is set in copy editor's information of json allocation lists：
Word content ptext, font tfont, word anglec of rotation tangle, the center point coordinate value of text input box（Tleft,
ttop）, the wide twidth and high theight of text input box, the color tRGB of word, the time of occurrence point tbegin of word and
End time point tend, text importing is carried out according to the data in copy editor's information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410803625.1A CN104469179B (en) | 2014-12-22 | 2014-12-22 | A kind of method being attached to dynamic picture in mobile video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410803625.1A CN104469179B (en) | 2014-12-22 | 2014-12-22 | A kind of method being attached to dynamic picture in mobile video |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104469179A CN104469179A (en) | 2015-03-25 |
| CN104469179B true CN104469179B (en) | 2017-08-04 |
Family
ID=52914474
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410803625.1A Expired - Fee Related CN104469179B (en) | 2014-12-22 | 2014-12-22 | A kind of method being attached to dynamic picture in mobile video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104469179B (en) |
Families Citing this family (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104902282B (en) * | 2015-06-04 | 2018-09-11 | 深圳市明日空间信息技术有限公司 | The processing method and processing device of embedded watermark picture in video frame |
| CN104994312A (en) * | 2015-07-15 | 2015-10-21 | 北京金山安全软件有限公司 | Video generation method and device |
| CN106201251B (en) * | 2016-06-28 | 2019-06-11 | Oppo广东移动通信有限公司 | A kind of content of augmented reality determines method, device and mobile terminal |
| CN106373170A (en) * | 2016-08-31 | 2017-02-01 | 北京云图微动科技有限公司 | Video making method and video making device |
| CN106776831A (en) * | 2016-11-24 | 2017-05-31 | 维沃移动通信有限公司 | A kind of edit methods and mobile terminal of Multimedia Combination data |
| CN108346171B (en) * | 2017-01-25 | 2021-12-10 | 斑马智行网络(香港)有限公司 | Image processing method, device, equipment and computer storage medium |
| CN109587390B (en) * | 2017-09-29 | 2021-05-07 | 腾讯科技（深圳）有限公司 | Picture rendering method, picture rendering device and storage medium |
| CN107992246A (en) * | 2017-12-22 | 2018-05-04 | 珠海格力电器股份有限公司 | Video editing method and device and intelligent terminal |
| CN110062269A (en) * | 2018-01-18 | 2019-07-26 | 腾讯科技（深圳）有限公司 | Extra objects display methods, device and computer equipment |
| CN108259496B (en) * | 2018-01-19 | 2021-06-04 | 北京市商汤科技开发有限公司 | Method and device for generating special-effect program file package and special effect, and electronic equipment |
| CN108322673B (en) * | 2018-01-24 | 2021-08-10 | 北京小米移动软件有限公司 | Video generation method and video generation device |
| CN112860168B (en) * | 2018-02-08 | 2022-08-02 | 北京市商汤科技开发有限公司 | Method and device for generating special-effect program file package and special effect, and electronic equipment |
| CN113658298B (en) * | 2018-05-02 | 2024-09-17 | 北京市商汤科技开发有限公司 | Special effect program file package generation method and device |
| CN108717382B (en) * | 2018-05-11 | 2021-07-13 | 北京奇虎科技有限公司 | JSON structure-based audio and video file processing method and device and terminal equipment |
| CN108986227B (en) * | 2018-06-28 | 2022-11-29 | 北京市商汤科技开发有限公司 | Particle special effect program file package generation method and device and particle special effect generation method and device |
| CN109035373B (en) * | 2018-06-28 | 2022-02-01 | 北京市商汤科技开发有限公司 | Method and device for generating three-dimensional special effect program file package and method and device for generating three-dimensional special effect |
| CN108924622B (en) * | 2018-07-24 | 2022-04-22 | 腾讯科技（深圳）有限公司 | Video processing method and device, storage medium and electronic device |
| CN108882025B (en) * | 2018-08-07 | 2019-12-10 | 北京字节跳动网络技术有限公司 | Video frame processing method and device |
| CN110868631B (en) * | 2018-08-28 | 2021-12-14 | 腾讯科技（深圳）有限公司 | Video editing method, device, terminal and storage medium |
| CN111225232B (en) * | 2018-11-23 | 2021-10-29 | 北京字节跳动网络技术有限公司 | Video-based sticker animation engine, realization method, server and medium |
| CN114979766B (en) * | 2022-05-11 | 2023-11-21 | 深圳市闪剪智能科技有限公司 | Audio and video synthesis method, device, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101739712A (en) * | 2010-01-25 | 2010-06-16 | 四川大学 | Video-based 3D human face expression cartoon driving method |
| CN102055912A (en) * | 2009-10-29 | 2011-05-11 | 北京中星微电子有限公司 | Video application system, video special effect processing system and method |
| CN102202177A (en) * | 2010-03-26 | 2011-09-28 | 株式会社尼康 | Image processor, electronic camera, and image processing program |
| CN102355555A (en) * | 2011-09-22 | 2012-02-15 | 中国科学院深圳先进技术研究院 | Video processing method and system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4906034B2 (en) * | 2005-05-16 | 2012-03-28 | 富士フイルム株式会社 | Imaging apparatus, method, and program |
| JP5276454B2 (en) * | 2009-01-20 | 2013-08-28 | 安川情報システム株式会社 | Facial expression measurement method, facial expression measurement program, and facial expression measurement apparatus |
-
2014
- 2014-12-22 CN CN201410803625.1A patent/CN104469179B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102055912A (en) * | 2009-10-29 | 2011-05-11 | 北京中星微电子有限公司 | Video application system, video special effect processing system and method |
| CN101739712A (en) * | 2010-01-25 | 2010-06-16 | 四川大学 | Video-based 3D human face expression cartoon driving method |
| CN102202177A (en) * | 2010-03-26 | 2011-09-28 | 株式会社尼康 | Image processor, electronic camera, and image processing program |
| CN102355555A (en) * | 2011-09-22 | 2012-02-15 | 中国科学院深圳先进技术研究院 | Video processing method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104469179A (en) | 2015-03-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104469179B (en) | A kind of method being attached to dynamic picture in mobile video | |
| US11482192B2 (en) | Automated object selection and placement for augmented reality | |
| CN110650368B (en) | Video processing method and device and electronic equipment | |
| US11076142B2 (en) | Real-time aliasing rendering method for 3D VR video and virtual three-dimensional scene | |
| CN104219584B (en) | Panoramic video exchange method and system based on augmented reality | |
| CN104954769B (en) | A kind of immersion ultra high-definition processing system for video and method | |
| WO2017193576A1 (en) | Video resolution adaptation method and apparatus, and virtual reality terminal | |
| TWI520598B (en) | Image processing apparatus and image processing method | |
| CN106162203B (en) | Panoramic video playback method, player and wear-type virtual reality device | |
| CN104702928B (en) | Method of correcting image overlap area, recording medium, and execution apparatus | |
| CN105430471B (en) | The display methods and device of barrage in a kind of video | |
| CN107610044A (en) | Image processing method, computer-readable recording medium and virtual reality helmet | |
| CN107256136A (en) | Using superposition animation facilitate by multiple users to media content while consume | |
| CN107529091A (en) | Video clipping method and device | |
| JP2020526125A (en) | Method and system for fusing user-specific content into video production | |
| CN104504447A (en) | Method and device for distributing virtual seat images | |
| CN104574491A (en) | Multi-lattice special effect rendering method and system based on mobile terminal platform | |
| CN108986232A (en) | A method of it is shown in VR and AR environment picture is presented in equipment | |
| CN105389090A (en) | Game interaction interface displaying method and apparatus, mobile terminal and computer terminal | |
| WO2023193521A1 (en) | Video inpainting method, related apparatus, device and storage medium | |
| CN102542300A (en) | Method for automatically recognizing human body positions in somatic game and display terminal | |
| CN111696034A (en) | Image processing method and device and electronic equipment | |
| CN106303493B (en) | Image processing method and device | |
| CN106803889A (en) | A kind of intelligent high-speed image capture method and its device in blast process | |
| CN115830210A (en) | Rendering method and device of virtual object, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20190626 Address after: 310000 8 blocks, No. 16, Zhuantang Science and Technology Economic Zone, Xihu District, Hangzhou City, Zhejiang Province Patentee after: Ali cloud computing Co., Ltd. Address before: 310000 2/F, Building 3, Lefuzhihui Park, 28 Xiangyuan Road, Gongshu District, Hangzhou City, Zhejiang Province Patentee before: HANGZHOU DUANQU NETWORK MEDIA TECHNOLOGY CO., LTD. |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170804 Termination date: 20191222 |