CN101141608A - Video instant communication system and method - Google Patents
Video instant communication system and method Download PDFInfo
- Publication number
- CN101141608A CN101141608A CNA2007101236492A CN200710123649A CN101141608A CN 101141608 A CN101141608 A CN 101141608A CN A2007101236492 A CNA2007101236492 A CN A2007101236492A CN 200710123649 A CN200710123649 A CN 200710123649A CN 101141608 A CN101141608 A CN 101141608A
- Authority
- CN
- China
- Prior art keywords
- people
- face
- face information
- video
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Compression Or Coding Systems Of Tv Signals (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The present invention relates to a system and a method for video instant communication. The system comprises a sending terminal (100) and a receiving terminal (200), the sending terminal (100) comprises a video receiving module, a face detection module, a face tracking module, a coding module, and a network communication module, and the coding module codes face information in a video sequence through a first coding algorithm, and codes inhuman face information through a second coding algorithm. The present invention applies the face recognition technology, the face detection technology, and the face tracking technology in the video instant communication, the face information and the inhuman face information adopt different coding algorithms, the information quantity is effectively reduced after being coded, and a band width is reduced; further, the inhuman face information can also be discarded, the operation quantity of the band width is further reduced, and the quality of the video communication is increased; the face information can also adopt the special algorithm, the face information is highlighted, and the user experience is increased.
Description
Technical field
The present invention relates to instant messaging (IM) field, be specifically related to video instant communication system and method, more particularly, relate to video instant communication system and method based on detection of people's face and face tracking.
Background technology
Along with popularizing and the lifting of the network bandwidth of instant messaging, increasing user begins to carry out Video chat, video calling, video conference etc. with camera.In video instant communication, the both sides that carry out video communication often relatively pay close attention to the particular video frequency content of picture frame (for example, people's face), and other information (as background) are not too paid close attention to.In the existing video instant communication system, transmitting terminal is by video input apparatus such as camera receiver, video sequence, and adopt certain encryption algorithm that picture frame is encoded, that is to say, transmitting terminal uses the encode various piece (for example each image block of a picture frame) of a picture frame of identical encryption algorithm, and this has brought two problems:
(1), afterwards the image frame information amount is bigger for coding, takies bigger bandwidth.Be easy to cause the difficult quality guarantee of video because of the instability of the network bandwidth and transmission quality.
(2), can not give prominence to the particular video information (for example people's face) in the picture frame effectively, can not satisfy video communication both sides' video communication well and experience.
Generally speaking, what the both sides that communicate relatively paid close attention to is the other side's facial information, degree of concern for background information obviously reduces, and therefore, needs a kind of video instant communication method and system that takies less bandwidth and can give prominence to people's face and desalinate background.
On the other hand, along with computer automation, intelligentized development, recognition of face, people's face detection and tracking technology have had very big progress.For example Chinese patent application 200510135668.8, and " the real-time detection of people's face and the lasting method and system of following the tracks of in the video sequence " just put down in writing the method and system of video sequence being carried out the detection and tracking of people's face.Therefore, existing recognition of face, detection and tracking technology have been the improvement of video instant communication system and method, and technical conditions are provided.
Summary of the invention
The technical problem to be solved in the present invention is, the entire image frame is adopted identical encryption algorithm and the occupied bandwidth that causes, the defective that can not give prominence to particular video information at existing and video system communication system, a kind of improved video instant communication system and method are provided.
On the one hand, the invention provides a kind of video instant communication system, comprise transmitting terminal and receiving terminal, described transmitting terminal comprises the video reception module that is used for receiving video signals and generates video sequence, wherein:
Described transmitting terminal also comprises:
People's face detection module is used for described video sequence is detected, and determines whether comprise people's face information in the two field picture;
The face tracking module is used for after certain two field picture detects people's face information, follows the trail of and analyze people's face information of subsequent frame;
Coding module, it is encoded to the people's face information in the described video sequence with first encryption algorithm, the non-face information in the described video sequence is encoded or abandons non-face information with second encryption algorithm;
Network communication module is used to send the video information of coding.
In video instant communication system of the present invention:
Described transmitting terminal also comprises the model parameter storehouse; And
Described people's face detection module also extracts people's face information of current image frame and it is deposited in the model parameter storehouse.
In video instant communication system of the present invention, described people's face detection module uses the people's face detection algorithm based on gray level model that described video sequence is detected.
In video instant communication system of the present invention, described people's face detection module uses the people's face detection algorithm based on complexion model that described video sequence is detected.
In video instant communication system of the present invention, described face tracking module is used based drive tracking, is made up people's face information of following the trail of and analyzing subsequent frame based on the tracking of model or its.
On the other hand, the invention provides a kind of method of video instant communication, may further comprise the steps:
S1, transmitting terminal receiver, video sequence;
Whether S2, the present frame that detects in the described video sequence comprise people's face information, if, execution in step S3 then, otherwise, continue to detect subsequent frame to determine whether it comprises people's face information;
S3, in step S2, detect certain frame and comprise after people's face information, follow the trail of and analyze people's face information of subsequent frame;
S4, the people's face information in the described video sequence is encoded, the non-face information in the described video sequence is encoded or abandon non-face information with second encryption algorithm with first encryption algorithm.
In video instant communication method of the present invention, described step S2 further comprises people's face information of also extracting current image frame and it is deposited in the model parameter storehouse.
In video instant communication method of the present invention, described step S2 further comprises: if present frame does not comprise people's face information, then present frame is carried out normal encoding.
In video instant communication method of the present invention, described step S2 comprises that further use detects described video sequence based on people's face detection algorithm of complexion model.
In video instant communication method of the present invention, described step S2 comprises that further use detects described video sequence based on people's face detection algorithm of complexion model.
In video instant communication method of the present invention, described step S3 further comprises and uses based drive tracking, makes up people's face information of following the trail of and analyzing subsequent frame based on the tracking of model or its.
Compared with prior art, the present invention has following beneficial effect:
1, recognition of face, the detection of people's face, face tracking technology are applied in the video instant communication, distinguish people's face information and non-face information in the picture frame effectively, and, reduce the amount of information after encoding effectively to people's face information and the different encryption algorithm of non-face information employing, reduce bandwidth;
If 2 network qualities are bad, can discard non-face information, further reduce the bandwidth use amount, increase the quality of video communication;
3, can adopt special algorithm to people's face information, outstanding people's face information increases user experience.
Description of drawings
The invention will be further described below in conjunction with drawings and Examples, in the accompanying drawing:
Fig. 1 is the framework schematic diagram of video instant communication system of the present invention;
Even Fig. 2 is people's face detection module of video communication system of the present invention, the structural representation of face tracking module;
Fig. 3 is the flow chart of video instant communication method of the present invention.
Embodiment
Human face detection tech
People's face detects the process that (Face Detection) is meant the position of determining everyone face (if existence) in input picture, size, pose.The detection of people's face is a key technology in the information processing of people's face.
The pattern feature that facial image comprised is very abundant, comprises 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.In these features which be the most useful, how to utilize these features, be that people's face detects and will study a key issue.People's face pattern has complicated and careful variation, therefore generally needs to adopt the method for various modes characteristic synthetic, as simple combination, statistical inference, fuzzy decision, machine learning etc.Conclusion is got up, and method for detecting human face can be divided into based on the method for features of skin colors (complexion model) with based on method two classes of gray feature (gray level model) according to the color attribute that utilizes feature.The former is applicable to that constructing fast people's face detects and the face tracking algorithm, The latter people's face be different from the more essential feature of other object, be the emphasis that people's face detection range is studied.The different models that adopt during according to characteristic synthetic can be divided into the method based on gray feature two big classes: based on the method for heuristic (knowledge) model with based on the method for statistical model.
The face tracking technology
The face tracking technology normally on the basis that people's face detects for video sequence in the tracking of people's face movement position.The face tracking technology comprises based on the method for motion (Motion-based) and based on the method for model (Model-based).The former adopts methods such as motion segmentation, light stream, stereoscopic vision, utilizes track human faces motions such as space-time gradient, Kalman filter; The latter 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.In face tracking, often be used in combination this two kinds of methods.
For example, Chinese patent application CN200510135668.8 has just put down in writing a kind of " the real-time detection of people's face and the method and system that continue to follow the tracks of in the video sequence ".
Embodiment one
Fig. 1 is the framework schematic diagram of the video instant communication system of one embodiment of the present of invention.As shown in Figure 1, video instant communication system of the present invention comprises transmitting terminal 100 and receiving terminal 200.Transmitting terminal 100 comprises video reception module 101, people's face detection module 103, face tracking module 105, coding module 107 and network communication module 109; Receiving terminal 200 comprises network communication module 201, decoder module 203, display module 205.
Fig. 2 is the structural representation of people's face detection module 103 and face tracking module 105.Below in conjunction with Fig. 1 and Fig. 2 the video instant communication system of present embodiment is described, in conjunction with Fig. 3 the video instant communication method of present embodiment is described simultaneously.
Shown in step 301, video reception module 101 receiving video signals also generate video sequence, for example, receive the vision signal of camera and generate video sequence.
Shown in step 303,103 pairs of video sequences of people's face detection module detect, and determine whether comprise people's face information in the two field picture.When operation, the video sequence of 103 pairs of inputs of people's face detection module carries out feature extraction, and the feature of extraction comprises face complexion, profile, histogram, motion vector etc., and these characteristics all can be put into model parameter storehouse 104 (with reference to figure 2).Do not detect under the situation of people's face if present frame is first frame or several frames of its preorder, 103 pairs of present frames of people's face detection module carry out people's face detecting operation, preferably adopt detection algorithm fast, as the people's face detection algorithm based on complexion model.In order to optimize testing result, can specify some agreed termses, for example only detect in the picture people's face of maximum or influential position, perhaps the size of people's face can not be too small etc.Certainly, also can adopt certain constraints, operation detects a plurality of people's faces.The technology of this respect also is comparatively ripe, and for example Chinese patent application CN200510120069.9 discloses a kind of method of utilizing human face detection tech and face tracking technology to follow the tracks of a plurality of people's faces in real time from video.
Shown in step 305, if people's face detection module 103 does not have to detect in certain frame people's face information, on the one hand, 107 pairs of image sequences of coding module carry out normal encoding (shown in step 306), enter step 311 then; On the other hand, 103 pairs of subsequent frames of people's face detection module detect (that is, being equivalent to turn back to step 303)." normal encoding " described here includes but not limited to the preset coding algorithm this picture frame integral body be encoded.
In the step 305, if detect people's face information at certain two field picture, on the one hand, and execution in step 309, promptly coding module 107 is encoded to people's face information with first encryption algorithm, with second encryption algorithm non-face information is encoded; On the other hand, shown in step 307, people's face information of subsequent frame is followed the trail of and analyzed to face tracking module 105, and people's face information of subsequent frame, non-face information are encoded (being equivalent to step 309) with first encryption algorithm, second encryption algorithm respectively.
Face tracking is that the video pictures content combination analysis by statistics that provides in the model parameter storehouse 104 and present frame obtains.Face tracking can be analyzed according to front detected people's face information, and obtains the movable information of people's face, for coding stage of back great role is arranged also at movable information that tracking phase obtained.
Be noted that under the common situation, adopt the picture quality after first encryption algorithm is encoded, be better than the picture quality that adopts after second encryption algorithm is encoded, that is, the people's face quality of information behind the coding is better than the quality of non-face information (for example background information).In addition, in a preferred embodiment, the picture quality behind above-mentioned " preset coding algorithm " coding is better than or equals second encryption algorithm.But those skilled in the art will realize that the present invention is not limited to this.For example, under the situation of network condition bad (for example, bandwidth is very limited), can directly abandon non-face information, this scheme also should fall into protection scope of the present invention.
In the step 309 specific to present embodiment, coding module 107 is encoded to the people's face information in the described video sequence with first encryption algorithm, with second encryption algorithm non-face information in the described video sequence is encoded.Like this, can guarantee encryption algorithm is absorbed in people's face, improve the information quality of people face part, strengthen user's experience.Under specific applied environment, for example the network bandwidth very under the condition of limited, can also abandon non-face information, transmission people's face information only, thus guaranteed carrying out smoothly of video communication.
In the step 311, the video information after network communication module 109 will be encoded sends to receiving terminal 200.
In the step 313, the network communication module 201 of receiving terminal 200 receives the video information of described coding.
In the step 315, the video information of 203 pairs of described codings of decoder module is decoded, and obtains people's face information, if coding module 107 does not abandon non-face information in the step 309, so, also obtains non-face information simultaneously.
Then, in the step 317, the information that 205 pairs of decodings of display module obtain (people's face information and/or non-face information) is handled, and the information after will handling at last sends to display device and shows.
Those skilled in the art will recognize, in video instant communication system, video communication can be two-way, and promptly transmitting terminal 100 and receiving terminal 200 integrate, but this does not depart from the scope of the present invention.
In another embodiment, in step 307, face tracking module 105 can if find that present frame does not contain people's face message, just be carried out " normal encoding " to this picture frame by following the trail of to judge whether present frame exists people's face message; Simultaneously, carry out system initialization, carry out people's face by 103 pairs of subsequent frames of people's face detection module and detect (being equivalent to return step 303).For example, after video carries out a period of time, the user has left video input apparatus, face tracking module 105 can detect the face information of having had no talent in the present frame at this moment, so, this frame is just encoded according to the mode of " normal encoding ", and simultaneity factor is carried out initialization, subsequently each frame is all carried out people's face detect till people's face occurs once more.
Claims (10)
1. a video instant communication system comprises transmitting terminal (100), and described transmitting terminal (100) comprises the video reception module (101) that is used for receiving video signals and generates video sequence, it is characterized in that, described transmitting terminal (100) also comprises:
People's face detection module (103) is used for described video sequence is detected, and determines whether comprise people's face information in the two field picture;
Face tracking module (105) is used for after certain two field picture detects people's face information, follows the trail of and analyze people's face information of subsequent frame;
Coding module (107), it is encoded to the people's face information in the described video sequence with first encryption algorithm, the non-face information in the described video sequence is encoded or abandons non-face information with second encryption algorithm;
Network communication module (109) is used to send the video information of coding.
2. system according to claim 1 is characterized in that:
Described transmitting terminal (100) also comprises model parameter storehouse (104);
Described people's face detection module (103) also extracts people's face information of current image frame and it is deposited in the model parameter storehouse (104).
3. system according to claim 1 and 2 is characterized in that, described people's face detection module (103) uses the people's face detection algorithm based on complexion model that described video sequence is detected.
4. system according to claim 1 and 2 is characterized in that, described people's face detection module (103) uses the people's face detection algorithm based on gray level model that described video sequence is detected.
5. system according to claim 1 and 2 is characterized in that, described face tracking module (105) is used based drive tracking, made up people's face information of following the trail of and analyzing subsequent frame based on the tracking of model or its.
6. the method for a video instant communication is characterized in that, may further comprise the steps:
S1, transmitting terminal receiver, video sequence;
Whether S2, the present frame that detects in the described video sequence comprise people's face information, if, execution in step S3 then, otherwise, continue to detect subsequent frame to determine whether it comprises people's face information;
S3, in step S2, detect certain frame and comprise after people's face information, follow the trail of and analyze people's face information of subsequent frame;
S4, the people's face information in the described video sequence is encoded, the non-face information in the described video sequence is encoded or abandon non-face information with second encryption algorithm with first encryption algorithm;
The video information of S5, transmission coding.
7. method according to claim 6 is characterized in that, described step S2 further comprises people's face information of also extracting current image frame and it is deposited in the model parameter storehouse.
8. method according to claim 6 is characterized in that, described step S2 further comprises: if present frame does not comprise people's face information, then present frame is carried out normal encoding.
9. according to any described method in the claim 6 to 8, it is characterized in that described step S2 comprises that further use detects described video sequence based on people's face detection algorithm of complexion model.
10. according to any described method in the claim 6 to 8, it is characterized in that described step S3 further comprises and uses based drive tracking, makes up people's face information of following the trail of and analyzing subsequent frame based on the tracking of model or its.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2007101236492A CN101141608B (en) | 2007-09-28 | 2007-09-28 | Video instant communication system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2007101236492A CN101141608B (en) | 2007-09-28 | 2007-09-28 | Video instant communication system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101141608A true CN101141608A (en) | 2008-03-12 |
| CN101141608B CN101141608B (en) | 2011-05-11 |
Family
ID=39193309
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2007101236492A Active CN101141608B (en) | 2007-09-28 | 2007-09-28 | Video instant communication system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101141608B (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101505430B (en) * | 2008-09-18 | 2011-05-11 | 西南交通大学 | Intra-frame updating method for head and shoulder video sequence |
| CN102194443A (en) * | 2010-03-04 | 2011-09-21 | 腾讯科技（深圳）有限公司 | Display method and system for window of video picture in picture and video processing equipment |
| WO2012000135A1 (en) * | 2010-07-02 | 2012-01-05 | Intel Corporation | Face detecting method and apparatus |
| CN102411783A (en) * | 2010-10-14 | 2012-04-11 | 微软公司 | Automatically tracking user movement in a video chat application |
| CN103442202A (en) * | 2013-08-22 | 2013-12-11 | 北京智谷睿拓技术服务有限公司 | Video communication method and device |
| CN101841704B (en) * | 2009-01-14 | 2013-12-11 | 北京中星微电子有限公司 | Method and device for compressing and decompressing video bit stream |
| CN103458215A (en) * | 2012-05-29 | 2013-12-18 | 国基电子（上海）有限公司 | Video call switching system, cellphone, electronic device and switching method |
| WO2014094216A1 (en) * | 2012-12-18 | 2014-06-26 | Intel Corporation | Multiple region video conference encoding |
| CN104023216A (en) * | 2014-05-28 | 2014-09-03 | 清华大学 | Face video compression method |
| CN104904203A (en) * | 2013-09-30 | 2015-09-09 | 酷派软件技术（深圳）有限公司 | Methods and systems for image encoding and decoding and terminal |
| CN105745920A (en) * | 2013-11-19 | 2016-07-06 | 微软技术许可有限责任公司 | Video transmission |
| CN105960801A (en) * | 2014-02-03 | 2016-09-21 | 谷歌公司 | Enhancing video conferences |
| WO2018023895A1 (en) * | 2016-08-05 | 2018-02-08 | 中兴通讯股份有限公司 | Method, device and system for controlling video call, and computer storage medium |
| WO2018138582A1 (en) * | 2017-01-27 | 2018-08-02 | Banuba Limited | Computer systems and computer-implemented methods specialized in processing electronic image data |
| CN109995992A (en) * | 2018-01-02 | 2019-07-09 | 上海银晨智能识别科技有限公司 | Image-pickup method and device, computer readable storage medium |
| CN110557649A (en) * | 2019-09-12 | 2019-12-10 | 广州华多网络科技有限公司 | Live broadcast interaction method, live broadcast system, electronic equipment and storage medium |
| CN111416939A (en) * | 2020-03-30 | 2020-07-14 | 咪咕视讯科技有限公司 | Video processing method, video processing equipment and computer readable storage medium |
| WO2020151443A1 (en) * | 2019-01-23 | 2020-07-30 | 广州视源电子科技股份有限公司 | Video image transmission method, device, interactive intelligent tablet and storage medium |
| CN111654660A (en) * | 2020-06-08 | 2020-09-11 | 上海纽菲斯信息科技有限公司 | Video conference system coding transmission method based on image segmentation |
| CN112235531A (en) * | 2020-10-15 | 2021-01-15 | 北京字节跳动网络技术有限公司 | Video processing method, device, terminal and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5764803A (en) * | 1996-04-03 | 1998-06-09 | Lucent Technologies Inc. | Motion-adaptive modelling of scene content for very low bit rate model-assisted coding of video sequences |
| CN100538498C (en) * | 2003-07-15 | 2009-09-09 | 欧姆龙株式会社 | Object determination device and camera head |
-
2007
- 2007-09-28 CN CN2007101236492A patent/CN101141608B/en active Active
Cited By (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101505430B (en) * | 2008-09-18 | 2011-05-11 | 西南交通大学 | Intra-frame updating method for head and shoulder video sequence |
| CN101841704B (en) * | 2009-01-14 | 2013-12-11 | 北京中星微电子有限公司 | Method and device for compressing and decompressing video bit stream |
| CN102194443B (en) * | 2010-03-04 | 2014-12-10 | 腾讯科技（深圳）有限公司 | Display method and system for window of video picture in picture and video processing equipment |
| CN102194443A (en) * | 2010-03-04 | 2011-09-21 | 腾讯科技（深圳）有限公司 | Display method and system for window of video picture in picture and video processing equipment |
| WO2012000135A1 (en) * | 2010-07-02 | 2012-01-05 | Intel Corporation | Face detecting method and apparatus |
| CN102411783A (en) * | 2010-10-14 | 2012-04-11 | 微软公司 | Automatically tracking user movement in a video chat application |
| US9628755B2 (en) | 2010-10-14 | 2017-04-18 | Microsoft Technology Licensing, Llc | Automatically tracking user movement in a video chat application |
| CN102411783B (en) * | 2010-10-14 | 2016-07-06 | 微软技术许可有限责任公司 | Move from motion tracking user in Video chat is applied |
| CN103458215A (en) * | 2012-05-29 | 2013-12-18 | 国基电子（上海）有限公司 | Video call switching system, cellphone, electronic device and switching method |
| CN103458215B (en) * | 2012-05-29 | 2016-11-23 | 国基电子（上海）有限公司 | System, mobile phone, electronic installation and the changing method of Switch Video call |
| CN104782121A (en) * | 2012-12-18 | 2015-07-15 | 英特尔公司 | Multiple region video conference encoding |
| US20140341280A1 (en) * | 2012-12-18 | 2014-11-20 | Liu Yang | Multiple region video conference encoding |
| WO2014094216A1 (en) * | 2012-12-18 | 2014-06-26 | Intel Corporation | Multiple region video conference encoding |
| CN103442202A (en) * | 2013-08-22 | 2013-12-11 | 北京智谷睿拓技术服务有限公司 | Video communication method and device |
| CN103442202B (en) * | 2013-08-22 | 2017-09-26 | 北京智谷睿拓技术服务有限公司 | Video communication method and device |
| CN104904203A (en) * | 2013-09-30 | 2015-09-09 | 酷派软件技术（深圳）有限公司 | Methods and systems for image encoding and decoding and terminal |
| CN105745920B (en) * | 2013-11-19 | 2019-06-25 | 微软技术许可有限责任公司 | Transmission of video |
| CN105745920A (en) * | 2013-11-19 | 2016-07-06 | 微软技术许可有限责任公司 | Video transmission |
| CN105960801A (en) * | 2014-02-03 | 2016-09-21 | 谷歌公司 | Enhancing video conferences |
| CN105960801B (en) * | 2014-02-03 | 2020-02-07 | 谷歌有限责任公司 | Enhancing video conferencing |
| CN104023216A (en) * | 2014-05-28 | 2014-09-03 | 清华大学 | Face video compression method |
| CN104023216B (en) * | 2014-05-28 | 2017-02-15 | 清华大学 | Face video compression method |
| WO2018023895A1 (en) * | 2016-08-05 | 2018-02-08 | 中兴通讯股份有限公司 | Method, device and system for controlling video call, and computer storage medium |
| WO2018138582A1 (en) * | 2017-01-27 | 2018-08-02 | Banuba Limited | Computer systems and computer-implemented methods specialized in processing electronic image data |
| US10255483B2 (en) | 2017-01-27 | 2019-04-09 | Banuba Limited | Computer systems and computer-implemented methods specialized in tracking faces across visual representations |
| CN109995992A (en) * | 2018-01-02 | 2019-07-09 | 上海银晨智能识别科技有限公司 | Image-pickup method and device, computer readable storage medium |
| WO2020151443A1 (en) * | 2019-01-23 | 2020-07-30 | 广州视源电子科技股份有限公司 | Video image transmission method, device, interactive intelligent tablet and storage medium |
| CN110557649A (en) * | 2019-09-12 | 2019-12-10 | 广州华多网络科技有限公司 | Live broadcast interaction method, live broadcast system, electronic equipment and storage medium |
| CN110557649B (en) * | 2019-09-12 | 2021-12-28 | 广州方硅信息技术有限公司 | Live broadcast interaction method, live broadcast system, electronic equipment and storage medium |
| CN111416939A (en) * | 2020-03-30 | 2020-07-14 | 咪咕视讯科技有限公司 | Video processing method, video processing equipment and computer readable storage medium |
| CN111654660A (en) * | 2020-06-08 | 2020-09-11 | 上海纽菲斯信息科技有限公司 | Video conference system coding transmission method based on image segmentation |
| CN112235531A (en) * | 2020-10-15 | 2021-01-15 | 北京字节跳动网络技术有限公司 | Video processing method, device, terminal and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101141608B (en) | 2011-05-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101141608B (en) | Video instant communication system and method | |
| US9117112B2 (en) | Background detection as an optimization for gesture recognition | |
| US10628700B2 (en) | Fast and robust face detection, region extraction, and tracking for improved video coding | |
| Chai et al. | Face segmentation using skin-color map in videophone applications | |
| Habili et al. | Segmentation of the face and hands in sign language video sequences using color and motion cues | |
| US9584814B2 (en) | Content adaptive background foreground segmentation for video coding | |
| US8514941B2 (en) | Method and apparatus for motion vector processing | |
| CN103002289B (en) | Video constant quality coding device for monitoring application and coding method thereof | |
| US8608073B2 (en) | System and method for robust real-time 1D barcode detection | |
| US20100060783A1 (en) | Processing method and device with video temporal up-conversion | |
| CN102194443B (en) | Display method and system for window of video picture in picture and video processing equipment | |
| CN100505840C (en) | Method and device for transmitting face synthesized video | |
| CN102271241A (en) | Image communication method and system based on facial expression/action recognition | |
| US9619887B2 (en) | Method and device for video-signal processing, transmitter, corresponding computer program product | |
| WO2008116400A1 (en) | A terminal, method and system for realizing video communication | |
| CN114363623A (en) | Image processing method, image processing apparatus, image processing medium, and electronic device | |
| CN103905821A (en) | Video coding method and device allowing human face to be recognized | |
| CN106851302A (en) | A kind of Moving Objects from Surveillance Video detection method based on intraframe coding compression domain | |
| Zhang et al. | Moving objects detection method based on brightness distortion and chromaticity distortion | |
| CN114359088A (en) | Method for coding specific target figure of video | |
| CN115761571A (en) | Video-based target retrieval method, device, equipment and storage medium | |
| CN110222647B (en) | Face in-vivo detection method based on convolutional neural network | |
| CN114332983A (en) | Face image definition detection method, face image definition detection device, electronic equipment and medium | |
| CN112200840A (en) | Moving object detection system in visible light and infrared image combination | |
| WO2014031538A1 (en) | Background detection as an optimization for gesture recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |