CN101068314A - Network video frequency showing method and system - Google Patents
Network video frequency showing method and system Download PDFInfo
- Publication number
- CN101068314A CN101068314A CNA2006101524601A CN200610152460A CN101068314A CN 101068314 A CN101068314 A CN 101068314A CN A2006101524601 A CNA2006101524601 A CN A2006101524601A CN 200610152460 A CN200610152460 A CN 200610152460A CN 101068314 A CN101068314 A CN 101068314A
- Authority
- CN
- China
- Prior art keywords
- human face
- face region
- video image
- video
- show program
- 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
Images
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
- H04N5/272—Means for inserting a foreground image in a background image, i.e. inlay, outlay
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Processing Or Creating Images (AREA)
- Digital Computer Display Output (AREA)
Abstract
A method for realizing network video show includes selecting preset video show program, obtaining video image of user, displaying video image and video show program in superposition way, regulating video show program and video image according to size and position of human face region in video image current frame and superposing regulated video image at hollow out region of regulated video slow program for displaying human face region completely. The network video show system is also disclosed.
Description
Technical field
The present invention relates to the Internet video field, particularly relate to a kind of network video frequency showing method and system
Background technology
At first, under the lower situation of the ability of transmitted data on network and deal with data, people can only carry out written communication on the net.The user is the input characters exchange of information on the network instant communication instrument, and the network instant communication instrument is converted to corresponding code information with this literal exchange of information and is sent to interchange the opposing party user, and decoding is converted to former literal exchange of information demonstration.Though written communication can be expressed both sides' the meaning, dull, experience sense is relatively poor.
Along with the enhancing of the ability of transmitted data on network and deal with data, people can carry out speech exchange on the net.Sound pick-up outfit is set on host computer, obtain the user speech exchange of information, the network instant communication instrument becomes corresponding code information with this speech exchange information processing, be sent to and exchange the opposing party user, decoding is converted to former voice exchange of information again, come out by the broadcast device plays, the opposing party user just can this speech exchange information of uppick.Though speech exchange is more convenient, simple, vivid inadequately, and experience sense is good inadequately.
At present, development of internet technology, the ability of transmitted data on network and deal with data is significantly promoted, people can set up a picture pick-up device on the net, obtain user speech exchange of information and video image information simultaneously, the network instant communication instrument is processed into corresponding code information with this speech exchange information and video image information, be sent to and exchange the opposing party user, by decoding technique reduction speech exchange information and video image information, by broadcast device plays voice messaging, show this video image again in the viewing area of network instant communication instrument.Like this, exchange both sides and can direct viewing arrive the other side's video image, hear the other side's sound, can also carry out Internet video and exchange in conjunction with written communication information.The exchange of information content that Internet video exchanges is very abundant, and dynamic, vivid.
But, existing Internet video pattern is but very single, as shown in Figure 1, be existing Video show display window schematic diagram, this Video show display window 10 just is made up of simple literal viewing area 11, literal input area 12 and video image viewing area 13.Wherein, the video image that video image viewing area 13 can only the simple displaying user.Often carry out the young man of Video show on the net, wish very much when Internet video exchanges, the chances that represent individual character can be arranged more, but existing Video show pattern is interesting and personalized not enough, is difficult to satisfy these requirements.
Summary of the invention
Technical problem to be solved by this invention provides a kind of network video frequency showing method and system, strengthens the interesting and personalized of Internet video, improves sense of experience of users.
A kind of network video frequency showing method of the present invention comprises: choose the video show program that presets; Obtain user video image; Described video image and the stack of described video show program are shown.
Preferably, by following step, described video image and the stack of described video show program are shown: detect the human face region in the described video image; Follow the tracks of moving of described human face region; According to the size and the position of the described human face region of video image present frame, adjust described video show program and described video image; With adjusting the rear video image overlay, make the complete demonstration of described human face region at the vacancy section of adjusting rear video show program.
Preferably,, detect the human face region in the described video image: utilize default people's face detection algorithm that video image is carried out check and analysis, until the size and the position that obtain described human face region by following step.
Preferably, by following step, follow the tracks of moving of described human face region; The size and the position of search window are set according to described human face region; In the video image present frame, calculate the color histogram of described search window; Calculate the color probability distribution graph of described search window; The color probability distribution graph of combining target human face region center and described search window, the default track algorithm of utilization calculates the described human face region of video image present frame center.
Preferably, described default track algorithm is: calculate target human face region cluster centre in conjunction with the color probability distribution graph of described target human face region center and described search window; According to target human face region cluster centre new target human face region is set; Overlap as new target human face region and cluster centre, obtain the described human face region of video image present frame center, user people's face and picture pick-up device distance, reach the swing of picture pick-up device with respect to user people's face; As not overlapping, recomputate target human face region cluster centre.
Preferably, also comprise: the described human face region of video image present frame center is as the target human face region center of video image next frame; Adjust the size and the position of described search window according to the variation at target human face region center.
Preferably, size and position according to the described human face region of video image present frame, adjusting described video show program and described video image is: according to the size of the described human face region of video image present frame, adjust the area size of described video show program, the vacancy section of described video show program and described video image size are adapted; According to the position of the described human face region of video image present frame, adjust described video image position, make the complete demonstration of described human face region.
Preferably, size and position according to the described human face region of video image present frame, adjusting described video show program and described video image is: the size and the position that obtain video image present frame human face region according to detection, adjust the position and the size of the vacancy section on the video show program, reach the position of each object on the video show program, make the complete demonstration of human face region in the described video image.
Preferably, described video show program is provided with literal, image and/or animation, and the middle part is provided with vacancy section.
A kind of network video frequency showing of the present invention system comprises: acquiring unit is used to choose the video show program that presets and obtains user video image; Synthesis unit is used for described video image and the stack of described video show program are shown.
Preferably, described adjustment unit comprises: detecting unit is used for detecting the human face region of described video image; Tracking cell is used to follow the tracks of moving of described human face region; Adjustment unit, be used for size and position according to the described human face region of video image present frame, adjust described video show program and described video image,, make the complete demonstration of described human face region adjusting the rear video image overlay at the vacancy section of adjusting rear video show program.
Compared with prior art, the present invention has the following advantages:
The present invention shows that with video show program and video image stack the user can select different video show program presentation individual characteies, strengthens the interesting and personalized of Internet video.
Preferably, the present invention detects the human face region in the video image, and moving of track human faces zone according to the size and the position of video image present frame human face region, adjusted video show program and video image position, makes human face region and video show program vacancy section overlapping.Prevent that effectively content shelters from people face part in the video image in the video show program, improve sense of experience of users.
Description of drawings
Fig. 1 is existing Video show display window schematic diagram;
Fig. 2 is a network video frequency showing method embodiment flow chart of the present invention;
Fig. 3 is video image of the present invention and video show program stack schematic diagram;
Fig. 4 is a video show method of adjustment embodiment flow chart of the present invention;
Fig. 5 is a network video frequency showing system embodiment schematic diagram of the present invention.
Embodiment
For above-mentioned purpose of the present invention, feature and advantage can be become apparent more, the present invention is further detailed explanation below in conjunction with the drawings and specific embodiments.
Core concept of the present invention is that video show program and video image stack are shown that the user can select different video show program presentation individual characteies, strengthens the interesting and personalized of Internet video.
The present invention presets a large amount of video show programs, and video show program shows certain artistic conception and characteristic by literal, image and the animation etc. that the surface is provided with.As model's video show program, which is provided with Chairman Mao's badge, quotation, and be printed on model's printed words, show very strong enterprising spirit; Dynamic video show program which is provided with the light of different colours, large-scale audio amplifier pattern etc., shows very strong innervation; Quiet ease video show program which is provided with mild hill, and limpid stream pattern etc. show peace and quiet, easy boundary.The size of video show program and the viewing area sizableness of internet exchange instrument, and the middle part is provided with a certain size vacancy section, is used to the user video image that superposes.
The user selects video show program according to oneself individual character, hobby, and the video show program of choosing is placed on the viewing area of internet exchange instrument.User's video image is superimposed on the vacancy section of video show program, like this, with user's video image with video show program in conjunction with showing again, form network video frequency showing.The internet exchange instrument can be sent to network video frequency showing the interchange the other user and locate to show, strengthens the interesting and personalized of Internet video, satisfies the demand that the young man shows individual character.
See also Fig. 2, be network video frequency showing method embodiment flow chart of the present invention, concrete steps are as follows:
Step 201, choose the video show program that presets;
Choose the video show program of the individual character that can show off in the video show library of programmes that presets, the video show program of choosing is placed on the media of communication viewing area.
Step 202, obtain user video image;
Equipment by camera obtains user video image, and this video image need show that generally less, video image is the face image based on the user in the viewing area of internet exchange instrument.
Step 203, the stack of video image and video show program is shown, form network video frequency showing.
Video image and video show program are superposeed.As shown in Figure 3, for video image of the present invention and video show program stack schematic diagram, be provided with vacancy section 311 in the middle of the video show program 31, video image 32 is superimposed upon on the vacancy section 311, forms network video frequency showing, shows in the viewing area of internet exchange instrument.
Video image is based on performance user's face feature, shelter from the face of video image for the picture that prevents video show program, the face that guarantees video image just in time is placed in the middle of the video show program vacancy section, the present invention carries out human face region to video image and detects, and the tracking human face region is mobile, according to the size of video image present frame human face region and the size of position adjustment video show program, and the position of video pictures, guarantee that the vacancy section that user face is placed on video show program hits exactly.
Human face region detects the process be meant the position of determining people's face in the video image of input, size, pose.The pattern feature that facial image comprised is very abundant, mainly contains color characteristic (colour of skin, color development etc.), contour feature, histogram feature, mosaic map mosaic feature, architectural feature, transform domain feature, template characteristic and heuristic feature etc.People's face pattern also has complicated and careful variation, and the therefore general method that adopts the utilization of various modes characteristic synthetic is carried out the detection of human face region.As the various modes feature is carried out simple combination, by statistical inference, fuzzy decision is finished human face region and is detected, and can also improve the accuracy rate that people's face detects by machine learning.
The present invention more preferably detection method is to utilize the color characteristic of people's face and contour feature to carry out the human face region detection, can carry out people's face so fast and detect, and improves detection efficiency.
Face tracking be on the basis that people's face detects for video sequence in the tracking of human face region movement position.Inventor's face tracking technique can adopt the method based on motion (Motion-based), utilize methods such as motion segmentation, light stream, stereoscopic vision, in conjunction with mode track human faces regional movements such as space-time gradient, Kalman filter, determine the human face region shift position again.Also can adopt the method based on model (Model-based), at first obtain the priori of target, the structure object module carries out Model Matching to each two field picture of importing by sliding window.Also above-mentioned two kinds of methods can be used in combination.
The present invention obtains the size of video image present frame human face region according to detection, can amplify or dwindles adjustment video show program, and the vacancy section of video show program and video image size are adapted.The ratio of dwindling has certain restriction, and the video show program after guaranteeing to dwindle is not less than the size of original video image.As amplify and adjust the viewing area that rear video show program surpasses the internet exchange instrument, video show program exceeds part will be by cutting.
The present invention also can obtain the size and the position of video image present frame human face region according to detection, adjusts the position and the size of the vacancy section on the video show program, reaches the position of each object on the video show program.The vacancy section and the video image size of video show program are adapted, and guarantee that human face region is not blocked by other object.
Simultaneously, the present invention is according to the position of video image present frame human face region, adjusts the video image position, and complete the showing of facial image guaranteed in the demonstration that more adjusted video image and video show program superposeed, and is not blocked.
Consult Fig. 4, be video show method of adjustment embodiment flow chart of the present invention, concrete steps are as follows:
Employing is carried out check and analysis based on people's face detection algorithm of AdaBoost (Adaptive Boosting) to the video image color, can obtain the size and the position of human face region.The present invention mainly detects in the video image maximum or the face complexion feature of remarkable position.If people's face is too small in the video image, detect again after then video image being amplified.In testing process,, then continue to detect next frame, up to detecting human face region if do not detect human face region at the first frame of video image.
AdaBoost people's face detection algorithm can be adjusted the fault rate of data processing adaptively according to the feedback of weak study, improves the accuracy of data processing.
Search window is used for determining the zone and the position of people's face, and the search window scope is slightly larger than human face region, with the human face region circle within its scope.The tracking of human face region is moving of the interior people's face of track-while-scan window scope, the treating capacity of data when reducing the human face region following calculation.The size of search window and position adjust accordingly along with the adjustment at target human face region center in the step 404.
The described human face region of video image present frame center is as the target human face region center of video image next frame;
The face tracking algorithm can adopt continuous adaptive mean deviation track algorithm (CAMShift), and the CAMShift algorithm is a kind of track algorithm based on the color probability distribution, and this algorithm is quick and effective to the mobile tracking of human face region, is fit to use in real time.
Color probability distribution graph according to video image previous frame target human face region center and search window, utilize the cluster centre of CAMShift algorithm computation previous frame target human face region, according to cluster centre new target human face region is set again, if new target human face region and above-mentioned cluster centre do not overlap, then recomputate the cluster centre of the target human face region of previous frame; If new target human face region and above-mentioned cluster centre overlap, then draw video image present frame human face region center, and the distance and the swing of camera and user's face.
Consult Fig. 5, for network video frequency showing system embodiment schematic diagram of the present invention, comprise acquiring unit 51 and synthesis unit 52, wherein synthesis unit 52 comprises detecting unit 521, tracking cell 522 and adjustment unit 523.
Acquiring unit 51 presets a large amount of video show programs, and video show program shows certain artistic conception and characteristic by literal, image and the animation etc. that the surface is provided with.The size of video show program and the viewing area sizableness of internet exchange instrument, and the middle part is provided with a certain size vacancy section, is used to the user video image that superposes.Acquiring unit 51 is selected video show program according to user's individual character, hobby, and acquiring unit 51 is placed on the video show program of choosing the viewing area of internet exchange instrument.
Acquiring unit 51 obtains user video image by instruments such as picture pick-up devices.Acquiring unit 51 is sent to synthesis unit 52 with video image and video show program.
Video image is based on performance user's face feature, shelter from the face of video image for the picture that prevents video show program, the face that guarantees video image just in time is placed in the middle of the video show program vacancy section, 52 pairs of video images of synthesis unit carry out human face region and detect, and the tracking human face region is mobile, according to the size of video image present frame human face region and the size of position adjustment video show program, and the position of video pictures, guarantee that the vacancy section that user face is placed on video show program hits exactly.
Detecting unit 521 is determined position, size, the pose of people's face in the video image of input.Detecting unit 521 utilizes the color characteristic of people's face and contour feature to carry out the human face region detection, can carry out people's face so fast and detect, and improves detection efficiency.Detecting unit 521 is sent to tracking cell 522 with size, the position data of detected human face region.
Tracking cell 522 on the basis that people's face detects for video sequence in the tracking of human face region movement position.Tracking cell 522 can adopt the method based on motion (Motion-based), utilizes methods such as motion segmentation, light stream, stereoscopic vision, in conjunction with mode track human faces regional movements such as space-time gradient, Kalman filter, determines the human face region shift position again.Tracking cell 522 also can adopt the method based on model (Model-based), at first obtains the priori of target, and the structure object module carries out Model Matching to each two field picture of importing by sliding window.Also above-mentioned two kinds of methods can be used in combination.Tracking cell 522 is sent to adjustment unit 523 with the size and the position of the video image present frame human face region that tracking obtains.
Simultaneously, adjustment unit 523 is according to the position of video image present frame human face region, adjusts the video image position, and complete the showing of facial image guaranteed in the demonstration that more adjusted video image and video show program superposeed, and is not blocked.
More than to a kind of video frequency showing method provided by the present invention and system, be described in detail, used specific case herein principle of the present invention and execution mode are set forth, the explanation of above embodiment just is used for helping to understand method of the present invention and core concept thereof; Simultaneously, for one of ordinary skill in the art, according to thought of the present invention, the part that all can change in specific embodiments and applications, in sum, this description should not be construed as limitation of the present invention.
Claims (11)
1, a kind of network video frequency showing method is characterized in that, comprising:
Choose the video show program that presets;
Obtain user video image;
Described video image and the stack of described video show program are shown.
2, method according to claim 1 is characterized in that, by following step, described video image and the stack of described video show program is shown:
Detect the human face region in the described video image;
Follow the tracks of moving of described human face region;
According to the size and the position of the described human face region of video image present frame, adjust described video show program and described video image;
With adjusting the rear video image overlay, make the complete demonstration of described human face region at the vacancy section of adjusting rear video show program.
3, method according to claim 2 is characterized in that, by following step, detects the human face region in the described video image:
Utilize default people's face detection algorithm that video image is carried out check and analysis, until the size and the position that obtain described human face region.
4, method according to claim 2 is characterized in that, by following step, follows the tracks of moving of described human face region;
The size and the position of search window are set according to described human face region;
In the video image present frame, calculate the color histogram of described search window;
Calculate the color probability distribution graph of described search window;
The color probability distribution graph of combining target human face region center and described search window, the default track algorithm of utilization calculates the described human face region of video image present frame center.
5, method according to claim 4 is characterized in that, described default track algorithm is:
Calculate target human face region cluster centre in conjunction with the color probability distribution graph of described target human face region center and described search window;
According to target human face region cluster centre new target human face region is set;
Overlap as new target human face region and cluster centre, obtain the described human face region of video image present frame center, user people's face and picture pick-up device distance, reach the swing of picture pick-up device with respect to user people's face; As not overlapping, recomputate target human face region cluster centre.
6, method according to claim 4 is characterized in that, also comprises:
The described human face region of video image present frame center is as the target human face region center of video image next frame;
Adjust the size and the position of described search window according to the variation at target human face region center.
7, method according to claim 2 is characterized in that, according to the size and the position of the described human face region of video image present frame, adjusts described video show program and described video image and is:
According to the size of the described human face region of video image present frame, adjust the area size of described video show program, the vacancy section of described video show program and described video image size are adapted;
According to the position of the described human face region of video image present frame, adjust described video image position, make the complete demonstration of described human face region.
8, method according to claim 2 is characterized in that, according to the size and the position of the described human face region of video image present frame, adjusts described video show program and described video image and is:
Obtain the size and the position of video image present frame human face region according to detection, adjust the position and the size of the vacancy section on the video show program, and the position of each object on the video show program, make the complete demonstration of human face region in the described video image.
According to each described method of claim 1 to 8, it is characterized in that 9, described video show program is provided with literal, image and/or animation, the middle part is provided with vacancy section.
10, a kind of network video frequency showing system is characterized in that, comprising:
Acquiring unit is used to choose the video show program that presets and obtains user video image;
Synthesis unit is used for described video image and the stack of described video show program are shown.
11, system according to claim 10 is characterized in that, described adjustment unit comprises:
Detecting unit is used for detecting the human face region of described video image;
Tracking cell is used to follow the tracks of moving of described human face region;
Adjustment unit, be used for size and position according to the described human face region of video image present frame, adjust described video show program and described video image,, make the complete demonstration of described human face region adjusting the rear video image overlay at the vacancy section of adjusting rear video show program.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNA2006101524601A CN101068314A (en) | 2006-09-29 | 2006-09-29 | Network video frequency showing method and system |
PCT/CN2007/070667 WO2008040215A1 (en) | 2006-09-29 | 2007-09-11 | Network video displaying method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNA2006101524601A CN101068314A (en) | 2006-09-29 | 2006-09-29 | Network video frequency showing method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN101068314A true CN101068314A (en) | 2007-11-07 |
Family
ID=38880735
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CNA2006101524601A Pending CN101068314A (en) | 2006-09-29 | 2006-09-29 | Network video frequency showing method and system |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN101068314A (en) |
WO (1) | WO2008040215A1 (en) |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101807393A (en) * | 2010-03-12 | 2010-08-18 | 青岛海信电器股份有限公司 | KTV system, implement method thereof and TV set |
WO2010148848A1 (en) * | 2009-06-23 | 2010-12-29 | 腾讯科技(深圳)有限公司 | Method, device and system for enabling interaction between video and virtual network scene |
CN102231272A (en) * | 2011-01-21 | 2011-11-02 | 辜进荣 | Method and device for synthesizing network videos and audios |
CN101674411B (en) * | 2008-09-09 | 2012-04-04 | 卡西欧计算机株式会社 | Image capturing apparatus, method of determining presence or absence of image area, and recording medium |
CN102467323A (en) * | 2010-11-09 | 2012-05-23 | 由田新技股份有限公司 | System for displaying guest images for interaction |
CN102592127A (en) * | 2010-11-24 | 2012-07-18 | 索尼公司 | Information processing device, information processing method and computer program product |
CN103607554A (en) * | 2013-10-21 | 2014-02-26 | 无锡易视腾科技有限公司 | Fully-automatic face seamless synthesis-based video synthesis method |
CN103905733A (en) * | 2014-04-02 | 2014-07-02 | 哈尔滨工业大学深圳研究生院 | Method and system for conducting real-time tracking on faces by monocular camera |
CN103929669A (en) * | 2014-04-30 | 2014-07-16 | 成都理想境界科技有限公司 | Interactive video generator, player, generating method and playing method |
CN105046661A (en) * | 2015-07-02 | 2015-11-11 | 广东欧珀移动通信有限公司 | Method, apparatus and intelligent terminal for improving video beautification efficiency |
CN106330686A (en) * | 2016-09-28 | 2017-01-11 | 北京小米移动软件有限公司 | Message delivering method and apparatus |
CN106454155A (en) * | 2016-09-26 | 2017-02-22 | 新奥特(北京)视频技术有限公司 | Video shade trick processing method and device |
CN107273849A (en) * | 2010-09-13 | 2017-10-20 | 佳能株式会社 | Display control unit and display control method |
CN111521245A (en) * | 2020-07-06 | 2020-08-11 | 华夏天信(北京)智能低碳技术研究院有限公司 | Liquid level control method based on visual analysis |
CN111599080A (en) * | 2019-02-20 | 2020-08-28 | 深圳怡化电脑股份有限公司 | Spliced paper money detection method and device, financial machine tool equipment and storage medium |
CN113079328A (en) * | 2021-03-19 | 2021-07-06 | 北京有竹居网络技术有限公司 | Video generation method and device, storage medium and electronic equipment |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110136229B (en) * | 2019-05-27 | 2023-07-14 | 广州亮风台信息科技有限公司 | Method and equipment for real-time virtual face changing |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0924648B1 (en) * | 1997-12-18 | 2004-08-25 | Fuji Photo Film Co., Ltd. | Image processing apparatus and method |
JP2002281465A (en) * | 2001-03-16 | 2002-09-27 | Matsushita Electric Ind Co Ltd | Security protection processor |
JP2005184582A (en) * | 2003-12-22 | 2005-07-07 | Canon Inc | Image input reproduction device, and image processing method in image input reproduction device |
-
2006
- 2006-09-29 CN CNA2006101524601A patent/CN101068314A/en active Pending
-
2007
- 2007-09-11 WO PCT/CN2007/070667 patent/WO2008040215A1/en active Application Filing
Cited By (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101674411B (en) * | 2008-09-09 | 2012-04-04 | 卡西欧计算机株式会社 | Image capturing apparatus, method of determining presence or absence of image area, and recording medium |
CN101930284B (en) * | 2009-06-23 | 2014-04-09 | 腾讯科技(深圳)有限公司 | Method, device and system for implementing interaction between video and virtual network scene |
WO2010148848A1 (en) * | 2009-06-23 | 2010-12-29 | 腾讯科技(深圳)有限公司 | Method, device and system for enabling interaction between video and virtual network scene |
CN101930284A (en) * | 2009-06-23 | 2010-12-29 | 腾讯科技(深圳)有限公司 | Method, device and system for implementing interaction between video and virtual network scene |
US9247201B2 (en) | 2009-06-23 | 2016-01-26 | Tencent Holdings Limited | Methods and systems for realizing interaction between video input and virtual network scene |
RU2518940C2 (en) * | 2009-06-23 | 2014-06-10 | Тенсент Текнолоджи (Шэньчжэнь) Компани Лимитед | Method, apparatus and system for interlinking video image and virtual network environment |
CN101807393A (en) * | 2010-03-12 | 2010-08-18 | 青岛海信电器股份有限公司 | KTV system, implement method thereof and TV set |
CN101807393B (en) * | 2010-03-12 | 2012-12-19 | 青岛海信电器股份有限公司 | KTV system, implement method thereof and TV set |
CN107273849A (en) * | 2010-09-13 | 2017-10-20 | 佳能株式会社 | Display control unit and display control method |
CN107273849B (en) * | 2010-09-13 | 2021-02-26 | 佳能株式会社 | Display control device and display control method |
CN102467323A (en) * | 2010-11-09 | 2012-05-23 | 由田新技股份有限公司 | System for displaying guest images for interaction |
CN102592127A (en) * | 2010-11-24 | 2012-07-18 | 索尼公司 | Information processing device, information processing method and computer program product |
CN102231272A (en) * | 2011-01-21 | 2011-11-02 | 辜进荣 | Method and device for synthesizing network videos and audios |
CN103607554A (en) * | 2013-10-21 | 2014-02-26 | 无锡易视腾科技有限公司 | Fully-automatic face seamless synthesis-based video synthesis method |
CN103905733A (en) * | 2014-04-02 | 2014-07-02 | 哈尔滨工业大学深圳研究生院 | Method and system for conducting real-time tracking on faces by monocular camera |
CN103905733B (en) * | 2014-04-02 | 2018-01-23 | 哈尔滨工业大学深圳研究生院 | A kind of method and system of monocular cam to real time face tracking |
CN103929669A (en) * | 2014-04-30 | 2014-07-16 | 成都理想境界科技有限公司 | Interactive video generator, player, generating method and playing method |
CN103929669B (en) * | 2014-04-30 | 2018-01-05 | 成都理想境界科技有限公司 | Can interactive video maker, player and its generation method, player method |
CN105046661B (en) * | 2015-07-02 | 2018-04-06 | 广东欧珀移动通信有限公司 | A kind of method, apparatus and intelligent terminal for lifting video U.S. face efficiency |
CN105046661A (en) * | 2015-07-02 | 2015-11-11 | 广东欧珀移动通信有限公司 | Method, apparatus and intelligent terminal for improving video beautification efficiency |
CN106454155A (en) * | 2016-09-26 | 2017-02-22 | 新奥特(北京)视频技术有限公司 | Video shade trick processing method and device |
CN106330686A (en) * | 2016-09-28 | 2017-01-11 | 北京小米移动软件有限公司 | Message delivering method and apparatus |
CN111599080A (en) * | 2019-02-20 | 2020-08-28 | 深圳怡化电脑股份有限公司 | Spliced paper money detection method and device, financial machine tool equipment and storage medium |
CN111521245A (en) * | 2020-07-06 | 2020-08-11 | 华夏天信(北京)智能低碳技术研究院有限公司 | Liquid level control method based on visual analysis |
CN113079328A (en) * | 2021-03-19 | 2021-07-06 | 北京有竹居网络技术有限公司 | Video generation method and device, storage medium and electronic equipment |
CN113079328B (en) * | 2021-03-19 | 2023-03-28 | 北京有竹居网络技术有限公司 | Video generation method and device, storage medium and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
WO2008040215A1 (en) | 2008-04-10 |
WO2008040215A8 (en) | 2009-04-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101068314A (en) | Network video frequency showing method and system | |
WO2022001593A1 (en) | Video generation method and apparatus, storage medium and computer device | |
EP3879843A1 (en) | Video processing method and apparatus, electronic device, and computer-readable medium | |
Cheng et al. | Video adaptation for small display based on content recomposition | |
GB2563136A (en) | Augmented reality apparatus and method | |
CN100345085C (en) | Method for controlling electronic game scene and role based on poses and voices of player | |
CN107230187A (en) | The method and apparatus of multimedia signal processing | |
CN112367551B (en) | Video editing method and device, electronic equipment and readable storage medium | |
CN102741879A (en) | Method for generating depth maps from monocular images and systems using the same | |
WO2014184417A1 (en) | Method, apparatus and computer program product to represent motion in composite images | |
CN107911644A (en) | The method and device of video calling is carried out based on conjecture face expression | |
CN1908962A (en) | People face track display method and system for real-time robust | |
EP3635719A1 (en) | Systems and methods for generating a summary storyboard from a plurality of image frames | |
CN102271241A (en) | Image communication method and system based on facial expression/action recognition | |
CN104240277A (en) | Augmented reality interaction method and system based on human face detection | |
CN102157007A (en) | Performance-driven method and device for producing face animation | |
CN102194443A (en) | Display method and system for window of video picture in picture and video processing equipment | |
CN1968395A (en) | Viewing window switching control method and system for video image | |
CN101047867A (en) | Method for correcting multi-viewpoint vedio color | |
CN101051457A (en) | Electronic entertainment system of movie karo OK | |
EP4273716A1 (en) | Video processing method, electronic device and readable medium | |
CN110345610A (en) | The control method and device of air conditioner, air-conditioning equipment | |
CN102074033A (en) | Method and device for animation production | |
CN1489112A (en) | Sports image detecting method | |
CN103647923B (en) | A kind of method for displaying image in video calling |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C12 | Rejection of a patent application after its publication | ||
RJ01 | Rejection of invention patent application after publication |