CN106034215A - Video conference method and system - Google Patents

Video conference method and system Download PDF

Info

Publication number
CN106034215A
CN106034215A CN201510113324.0A CN201510113324A CN106034215A CN 106034215 A CN106034215 A CN 106034215A CN 201510113324 A CN201510113324 A CN 201510113324A CN 106034215 A CN106034215 A CN 106034215A
Authority
CN
China
Prior art keywords
video
termination
trace regions
face
block
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
Application number
CN201510113324.0A
Other languages
Chinese (zh)
Inventor
吴季庭
罗志良
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Top Victory Investments Ltd
TPV Investment Co Ltd
Original Assignee
TPV Investment Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by TPV Investment Co Ltd filed Critical TPV Investment Co Ltd
Priority to CN201510113324.0A priority Critical patent/CN106034215A/en
Publication of CN106034215A publication Critical patent/CN106034215A/en
Pending legal-status Critical Current

Links

Abstract

The invention discloses a video conference system, comprising a plurality of terminal devices which transmit data through network online device; each terminal comprises an image acquisition module and a processing module electrically connected to the image acquisition module; the image acquisition module captures a plurality of original images according to a sequence; the processing module receives the original image and filters the original image to become a tracking area related to a human face block; the processing module determine a pre-stored image corresponding to the human face block by comparing with the tracking area and at least one face feature; and a plurality of digital data packets related to the pre-stored image are generated. As a result, the video conference method and system only need to transmit the digital data packet of the pre-stored image corresponding to the human face block through the network to hold a multi-party conference, which reduces network transmission quantity.

Description

Video-meeting method and system
Technical field
The present invention relates to a kind of image communication method and system, particularly relate to one and can reach low The video-meeting method of volume of transmitted data and system.
Background technology
In recent years, with network technology and the prosperity of image processing techniques, the network teleconference becomes The important technology communicated with one another for the commercial affairs or kinsfolk that are in strange land.It is said that in general, it is existing Some video conference practices are i.e. setting up virtual meeting room, allow convention goer be entered by network Enter this virtual conference room to exchange, and borrow Network Synchronization to transmit participant and site thereof Sound, image etc., the participant in many ways from various places all can be carried out together with being personally on the scene Meeting.
But, when holding Multi-Party Conference in existing video conference mode, if the people simultaneously reached the standard grade Number numerous (such as reaching up to a hundred people or thousands of people etc.), huge image data transmission quantity will take network Limited transmission bandwidth, so that there are feelings asynchronous, unsharp in the image presented, sound Shape so that video conference is difficult to smooth and easy carrying out.
Summary of the invention
One of present invention purpose is that providing a kind of is effectively reduced regarding of image data transmission quantity Frequently conference method.
The video-meeting method of the present invention performs by a video conferencing system, this video conference system System includes multiple termination each other by network on-line transmission data, and this video conference Method comprises a step (A), a step (B), a step (C), a step (D), And a step (E).
It is multiple former that this step (A) is that each termination sequentially captured at interval of a scheduled time Beginning image.
This step (B) is that each termination described raw video of filtration becomes one to be relevant to a people The trace regions of face block.
This step (C) is each this trace regions of termination comparison and at least one face characteristic Determining a pair should the figure that prestore of face block.
This step (D) is that each termination produces multiple numerals being relevant to this figure that prestores Data packet.
This step (E) is that described numerical data package is passed by each termination via this network Defeated.
It is preferred that the video-meeting method of the present invention, this step (B) includes a step (B1), And a step (B2).
This step (B1) is that each termination is accumulated i raw video to set up a reflection right As the reference background area do not moved,
This step (B2) is that (i+1) individual raw video is deducted this reference by each termination Background area and obtain this trace regions.
It is preferred that the video-meeting method of the present invention, in this step (C), each terminal Device scans the neck position of this trace regions and sentences according to a stored default skin tone value Whether this trace regions disconnected has the colour of skin block at neck position, if having, then this chases after to continue comparison Track region and this face characteristic determine should this figure that prestores of face block.
It is preferred that the video-meeting method of the present invention, this step (D) include a step (D1), One step (D2), and a step (D3).
This step (D1) is that each termination is by the trace regions of (i+1) individual raw video With the trace regions comparison of i-th raw video, whether foundation exists this same face block, Decide whether to produce (i+1) individual numerical data package,
This step (D2), if being that this face block of (D1) comparison exists, does not produces (i+1) Individual numerical data package, and repeat step (A),
This step (D3) if being that this face block of (D1) comparison does not exists, then produces (i+1) Individual numerical data package.
It is preferred that when any terminal device sends session request as first speaker, and another terminal When device accepts to ask called, this video-meeting method also comprises a step (F), and a step Suddenly (G).
This step (F) is that the face block of this trace regions and is stored at least by first speaker A pair should face characteristic character data prestore inventory pairing obtain attendant's inventory;And
This step (G) is that the user interface of first speaker shows this attendant's inventory.
Additionally, another object of the present invention is to provide a kind of realizes low image data transmission quantity Video conferencing system.
Video conferencing system of the present invention comprises multiple each other by network on-line transmission data Termination, and each termination includes an image acquisition module, and a processing module.
This image acquisition module sequentially captures multiple raw video at interval of a scheduled time.
This processing module filters described raw video and becomes a tracing Area being relevant to a face block Territory, and this trace regions of comparison and at least one face characteristic determine a pair should face block Prestore figure, so as to producing multiple numerical data packages being relevant to this figure that prestores, and by institute State numerical data package to transmit via this network.
It is preferred that this processing module i raw video of accumulation is set up a reflection object and is not moved Reference background area, and (i+1) individual raw video is deducted this reference background area and obtains To this trace regions.
It is preferred that this processing module scans the neck position of this trace regions and according to stored One default skin tone value judges whether this trace regions has the colour of skin block at neck position, if Have, then continue this trace regions of comparison and determine should face block be somebody's turn to do with this face characteristic Prestore figure.
It is preferred that this processing module comparison i-th and tracing Area of (i+1) individual raw video Whether territory exists this face block, decides whether to produce (i+1) individual numerical data package, If there is this face block, the most do not produce (i+1) individual numerical data package, if there is not this Face block, then produce (i+1) individual numerical data package.
It is preferred that each termination also includes that a detecting current data traffic of this network is for this shadow The flow prison capturing the scheduled time that described raw video is spaced is updated according to this as acquisition module Survey module, one for capturing the audio frequency acquisition module of an original audio, and one by this numerical data Package combines this original audio and produces the video module that output is audio-visual.
The beneficial effects of the present invention is: each termination is borrowed and is filtered into by described raw video This trace regions, and after picking out the face block in this trace regions, only passed by network The numerical data package of the figure that prestores corresponding to this face block defeated, so as to reducing network The effect of transmission quantity.
Accompanying drawing explanation
Other the feature of the present invention and effect, by reference to graphic embodiment clearly Present, wherein:
Fig. 1 is a schematic diagram, and an embodiment of video conferencing system of the present invention is described;And
Fig. 2 is a flow chart, illustrates that video conferencing system of the present invention implements a kind of video conference side
Method.
Detailed description of the invention
Refering to Fig. 1, an embodiment of video conferencing system of the present invention comprises multiple termination 1 (only illustrate in figure its two), each other by network on-line transmission data, and each terminal sets Put 1 and include flow monitoring modular 11, image acquisition module 12, audio frequency acquisition module 13, a video module 14, and a processing module 15 being electrically connected to aforementioned each module.
This flow monitoring module 11 detects the data traffic that this network is current.
This image acquisition module 12 sequentially captures multiple raw video at interval of a scheduled time, And capture that described raw video is spaced predetermined is updated according to the current data traffic of this network Time.
This audio frequency acquisition module 13 is for capturing an original audio.
This processing module 15 processes described raw video and becomes multiple numerical data package, and by institute State numerical data package to transmit via this network.
This numerical data package is combined this original audio and produces output shadow by this video module 14 Sound, and include one for showing the user interface (not shown) of continuous image output.
Refering to Fig. 2, video conferencing system of the present invention performs a video-meeting method, and comprise with Lower step.
First, step 20 is to be detectd, by this flow monitoring module 11, the data traffic that side network is current.
Then, step 21 is sequentially to pick at interval of a scheduled time with this image acquisition module 12 Take multiple raw video.
Then, step 22 is to receive described raw video by means of this processing module 15, and filters institute State raw video and become a trace regions being relevant to a face block, and this step 22 include with Lower sub-step.
In sub-step 221, this processing module 15 accumulates i raw video, and to set up one anti- Mapping is as the reference background area do not moved.
In sub-step 222, (i+1) individual raw video is deducted this ginseng by this processing module 15 Examine background area and obtain this trace regions.
Then, step 23 is with this processing module 15 this trace regions of comparison and at least one face Feature determine a pair should the figure that prestore of face block, and this step 23 includes following son Step.
In sub-step 231, this processing module 15 judges that the face in this trace regions can Energy position, and continue down scan neck position and preset skin tone value comparison according to stored one Analyse whether the colour of skin block with neck position, to confirm whether this trace regions has truly Face.If comparison result is the colour of skin block without neck position, then this processing module 15 Judge that this trace regions does not have real human face, and repeat step 20;If comparison result is for having The colour of skin block at neck position, then whether this this face possible position of processing module 15 comparison has There is this colour of skin block, if having, then judging that this trace regions has real human face and performs sub-step 232;If nothing, then this processing module 15 judges that these personnel may wear the veils such as such as mask, And determine that this figure that prestores is the figure being relevant to the veils such as mask.
In sub-step 232, this processing module 15 is by this face this face of possible position comparison Feature and obtain this face block, and determine to should face block prestore figure for corresponding to The such as major part photograph of these personnel or cartoon figure etc..
Then, step 24 is produced by this processing module 15 and multiple is relevant to this figure that prestores Numerical data package, and this step 24 includes following sub-step.
In sub-step 241, this processing module 15 is by the tracing Area of (i+1) individual raw video Territory and the trace regions comparison of i-th raw video, according to whether there is this same face block, Decide whether to produce (i+1) individual numerical data package.
In sub-step 242, if this same face block of comparison exists, do not produce (i+1) Individual numerical data package, and repeat step 20.
In sub-step 243, if this same face block of comparison does not exists, then produce (i+1) Individual numerical data package.
Then, step 25 be this processing module 15 by described numerical data package via this network Transmission.
Then, step 26 is when any terminal device 1 sends session request as first speaker, And another termination 1 accept request called time, first speaker is by the face block of this trace regions With one store at least one pair of should the inventory pairing that prestore of character data of face characteristic, and note Note is judged the personnel wearing mask, and obtains attendant's inventory.
Then, step 27 is to be shown this attendant's inventory by the user interface of first speaker.
To sum up explanation understands, and video conferencing system of the present invention has the advantage that as follows.
One, only need in this network transmission to should face block prestore figure numerical data envelope Bag, reduces effect of volume of transmitted data.
If two current raw videos and previous raw video exist same face block, do not weigh Pass this numerical data package, further reduce volume of transmitted data.
Three, human face recognition is carried out by the face block of this trace regions, and at first speaker User interface shows this attendant's inventory, even if the personnel wearing mask also can be identified, with The situation of attending making personnel can effectively be grasped, therefore really can reach the purpose of the present invention.
As described above, only embodiments of the invention, when not limiting the present invention with this The scope implemented, the most all according to claims of the present invention and description made simple etc. Effect change and modification, the most still belong to the scope of the present invention.

Claims (10)

1. a video-meeting method, is performed by a video conferencing system, this video council Conference system includes multiple termination each other by network on-line transmission data, its feature It is: and this video-meeting method comprises:
(A) each termination sequentially captures multiple original at interval of one period of scheduled time Image;
(B) the described raw video of each termination filtration becomes one to be relevant to a people The trace regions of face block;
(C) each this trace regions of termination comparison is come with at least one face characteristic Determine one to should face block prestore figure;
(D) each termination produces multiple numerical datas being relevant to this figure that prestores Package;And
(E) described numerical data package is transmitted by each termination via this network.
Video-meeting method the most according to claim 1, it is characterised in that: this step Suddenly (B) including:
(B1) i raw video of each termination accumulation sets up a reflection object The reference background area do not moved,
(B2) (i+1) individual raw video is deducted this reference background by each termination Region and obtain this trace regions.
Video-meeting method the most according to claim 2, it is characterised in that: this step Suddenly (D) including:
(D1) each termination is by the trace regions of (i+1) individual raw video and the The trace regions comparison of i raw video, according to whether there is this same face block, Decide whether to produce (i+1) individual numerical data package,
(D2) if this same face block of (D1) comparison exists, (i+1) is not produced Individual numerical data package, and repeat step (A),
(D3) if this same face block of (D1) comparison does not exists, then (i+1) is produced Individual numerical data package.
Video-meeting method the most according to claim 1, it is characterised in that: when appointing One termination sends session request as first speaker, and another termination accepts to ask When asking called, this video-meeting method also comprises:
(F) face block of this trace regions is stored at least one with one by first speaker To should face characteristic character data prestore inventory pairing obtain attendant's inventory; And
(G) user interface of first speaker shows this attendant's inventory.
Video-meeting method the most according to claim 1, it is characterised in that: at this In step (C), each termination scans the neck position of this trace regions and according to institute The default skin tone value stored judges whether this trace regions has the colour of skin district at neck position Block, if having, then continues this trace regions of comparison and this face characteristic and determines should face This figure that prestores of block.
6. a video conferencing system, it is characterised in that: comprise:
Multiple termination, each other by network on-line transmission data, and each terminal Device includes:
One image acquisition module, sequentially captures multiple at interval of one period of scheduled time Raw video, and
One processing module, is electrically connected to this image acquisition module and receives described former Beginning image, and this processing module filter described raw video become one to be relevant to a face district The trace regions of block, and this trace regions of comparison and at least one face characteristic determine one To should face block prestore figure, so as to producing multiple numbers being relevant to this figure that prestores Digital data package, and described numerical data package is transmitted via this network.
Video conferencing system the most according to claim 6, it is characterised in that: at this Reason module is accumulated i raw video and is set up the reference background area that a reflection object does not moves Territory, and (i+1) individual raw video is deducted this reference background area and obtains this tracing Area Territory.
Video conferencing system the most according to claim 7, it is characterised in that: at this Whether the trace regions of reason module comparison i-th and (i+1) individual raw video exists this people Face block, decides whether to produce (i+1) individual numerical data package, if there is this face district Block, does not the most produce (i+1) individual numerical data package, if there is not this face block, then produces Raw (i+1) individual numerical data package.
Video conferencing system the most according to claim 6, it is characterised in that: at this Reason module scans the neck position of this trace regions and according to a stored default skin tone value Judging whether this trace regions has the colour of skin block at neck position, if having, then continuing comparison This trace regions and this face characteristic determine should this figure that prestores of face block.
Video conferencing system the most according to claim 6, it is characterised in that: each Individual termination also includes that a detecting current data traffic of this network is for this image acquisition module According to this update capture described raw video be spaced the flow monitoring module of the scheduled time, one The individual audio frequency acquisition module for capturing an original audio, and this numerical data sealed by one Inclusion is closed this original audio and produces the video module that output is audio-visual.
CN201510113324.0A 2015-03-16 2015-03-16 Video conference method and system Pending CN106034215A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510113324.0A CN106034215A (en) 2015-03-16 2015-03-16 Video conference method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510113324.0A CN106034215A (en) 2015-03-16 2015-03-16 Video conference method and system

Publications (1)

Publication Number Publication Date
CN106034215A true CN106034215A (en) 2016-10-19

Family

ID=57150081

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510113324.0A Pending CN106034215A (en) 2015-03-16 2015-03-16 Video conference method and system

Country Status (1)

Country Link
CN (1) CN106034215A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111918018A (en) * 2019-05-08 2020-11-10 奥图码科技股份有限公司 Video conference system, video conference apparatus, and video conference method

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1188948A (en) * 1996-12-27 1998-07-29 大宇电子株式会社 Method and apparatus for encoding facial movement
CN1731859A (en) * 2005-09-09 2006-02-08 北京中星微电子有限公司 Video compression method and video system using the method
CN101502088A (en) * 2006-10-11 2009-08-05 思科技术公司 Interaction based on facial recognition of conference participants
CN102647577A (en) * 2011-02-16 2012-08-22 鸿富锦精密工业(深圳)有限公司 Teleconference management system and management method
CN103517072A (en) * 2012-06-18 2014-01-15 联想(北京)有限公司 Video communication method and video communication equipment
CN101930535B (en) * 2009-06-25 2014-04-16 原相科技股份有限公司 Human face detection and tracking device

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1188948A (en) * 1996-12-27 1998-07-29 大宇电子株式会社 Method and apparatus for encoding facial movement
CN1731859A (en) * 2005-09-09 2006-02-08 北京中星微电子有限公司 Video compression method and video system using the method
CN101502088A (en) * 2006-10-11 2009-08-05 思科技术公司 Interaction based on facial recognition of conference participants
CN101930535B (en) * 2009-06-25 2014-04-16 原相科技股份有限公司 Human face detection and tracking device
CN102647577A (en) * 2011-02-16 2012-08-22 鸿富锦精密工业(深圳)有限公司 Teleconference management system and management method
CN103517072A (en) * 2012-06-18 2014-01-15 联想(北京)有限公司 Video communication method and video communication equipment

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111918018A (en) * 2019-05-08 2020-11-10 奥图码科技股份有限公司 Video conference system, video conference apparatus, and video conference method
CN111918018B (en) * 2019-05-08 2022-05-06 奥图码股份有限公司 Video conference system, video conference apparatus, and video conference method

Similar Documents

Publication Publication Date Title
KR101768980B1 (en) Virtual video call method and terminal
CN106231434B (en) A kind of living broadcast interactive special efficacy realization method and system based on Face datection
CN106161219B (en) Message treatment method and device
CN106454481B (en) A kind of method and device of live broadcast of mobile terminal interaction
CN109889855A (en) Intelligent panoramic net cast networked shopping system and method based on mobile APP
CN106992959A (en) A kind of 3D panoramas audio frequency and video live broadcast system and audio/video acquisition method
CN102209228A (en) Method and system for adapting a continuous presence layout according to interaction between conferees
CN101783889A (en) Real-time matting and video monitoring and collecting method
CN111405234A (en) Video conference information system and method with integration of cloud computing and edge computing
CN101431613A (en) Network group photo implementing method
CN104639777A (en) Conference control method, conference control device and conference system
CN109413359A (en) Camera tracking method, device and equipment
CN103369289A (en) Communication method of video simulation image and device
CN104506840B (en) A kind of real time tridimensional video splicing apparatus and close up method
CN103841358B (en) The video conferencing system and method for low code stream, sending ending equipment, receiving device
CN105247854A (en) Method and system for associating an external device to video conference session
CN109168059A (en) A kind of labial synchronization method playing audio & video respectively on different devices
CN105959614A (en) Method and system for processing video conference
CN112672174A (en) Split-screen live broadcast method, acquisition equipment, playing equipment and storage medium
CN104954804A (en) Self-adaptive image resolution processing method
US9277174B2 (en) Information processing apparatus, information processing method and information processing program
CN109963106B (en) Video image processing method and device, storage medium and terminal
CN100420298C (en) Digital sound control orienting method for camera site of camera
WO2015089944A1 (en) Method and device for processing picture of video conference, and conference terminal
CN103856742B (en) Processing method, the device and system of audiovisual information

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20161019