CN105049778A - Method and device for realizing video communication - Google Patents
Method and device for realizing video communication Download PDFInfo
- Publication number
- CN105049778A CN105049778A CN201510527270.2A CN201510527270A CN105049778A CN 105049778 A CN105049778 A CN 105049778A CN 201510527270 A CN201510527270 A CN 201510527270A CN 105049778 A CN105049778 A CN 105049778A
- Authority
- CN
- China
- Prior art keywords
- picture
- user
- anchor point
- current
- image
- 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
Landscapes
- Telephone Function (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses a method and device for realizing video communication. The method comprises the following steps: previously and respectively recording a corresponding relation between a first picture obtained through conventionally looking downward and a second picture obtained after a view angle is corrected in each of different locating point regions on a mobile terminal screen; when it is detected that the current picture is matched with the first picture in one locating point region in the video communication, replacing the current picture through the adoption of the second picture corresponding to the first picture. The current picture in the real-time video communication is replaced by the picture obtained after the view angle is corrected and recorded when a position of a camera is overlapped with the locating point, the view angles of the two parties in the video communication in the current video communication picture are corrected, the video communication quality is improved, and then the user experience is promoted.
Description
Technical field
The present invention relates to image processing techniques, espespecially a kind of method and device realizing video communication.
Background technology
At present, the front-facing camera that mobile terminal is arranged such as mobile phone, flat board etc. are upper is generally be placed on mobile phone screen top edges place, and generally neither the center at edge up, but side to the left or side to the right.
But when using mobile phone to carry out video communication, the picture of the other side is positioned at display screen middle, if look at the picture of the other side, then visual angle is in the below of camera, and when such the other side sees the picture of oneself, eyes are looked down.That is, based on the video communication of current mobile terminal, due to the relative position of camera and display screen, cause on picture that communicating pair sees, the eyes of the other side are looked down, instead of see oneself, like this, video communication is realized undesirable, reduce the quality of video communication, also have impact on Consumer's Experience.
Summary of the invention
In order to solve the problems of the technologies described above, the invention provides a kind of method and the device that realize video communication, can correcting video communicating pair visual angle, improve video communication quality, and then promote Consumer's Experience.
In order to reach the object of the invention, the invention provides a kind of method realizing video communication, comprising: distinguish the corresponding relation on record move terminal screen in different anchor point region between the first picture and the second picture in advance;
Carrying out in video communication, when detecting that current picture mates with the first picture in certain anchor point region, the second picture utilizing this first picture corresponding replaces current picture;
Wherein, the first picture is the conventional picture seen of directing one's eyes downward; Second picture is the picture after view angle correction.
Alternatively, also comprise before the method: obtain described first picture.
Alternatively, the screen of described mobile terminal pre-sets several anchor points; Described first picture of described acquisition comprises:
Keep user's face constant with described mobile terminal relative position.Screen shows anchor point successively, and for each anchor point, user's sight focuses on anchor point, and records current picture as described first picture.
Alternatively, also comprise before the method: obtain described second picture.
Alternatively, described acquisition second picture comprises:
According to the move mode pre-set, display reminding information on screen, to tell that user is when holding head position is constant, how to move mobile terminal, to make camera and the position at described each anchor point corresponding overlapping one by one, and often locating on overlapping position, record current picture is as described second picture.
Alternatively, described each anchor point records first picture of one or more users and the corresponding relation of the second picture respectively.
Alternatively, described current picture mates with the first picture in certain anchor point region and is: the picture of described current video communication is the most close with the first picture of certain anchor point record.
Alternatively, when carrying out described picture and replacing, the image of the eyeball between the upper lower eyelid utilizing the image of the eyeball between the upper lower eyelid in described second picture to replace in described current picture.
Alternatively, when described each anchor point preserves the corresponding relation of two or more users, in the process of described video calling, before the described replacement current picture of execution, also comprise:
Identify the user in current video call by facial characteristics, according to recognition result, choose second picture of user carrying out described replacement.
Present invention also offers a kind of device realizing video communication, at least comprise the first processing unit, the second processing unit; Wherein,
First processing unit, for the corresponding relation in advance respectively on record move terminal screen in different anchor point region between the first picture and the second picture;
Second processing unit, for carrying out in video communication, when detecting that current picture mates with the first picture in certain anchor point region, the second picture utilizing this first picture corresponding replaces current picture;
Wherein, the first picture is the conventional picture seen of directing one's eyes downward; Second picture is the picture after view angle correction.
Alternatively, described first processing module also for: obtain described first picture and described second picture.
Alternatively, described first processing unit comprises webcam driver module, and IMAQ and memory module; Wherein,
Webcam driver module for: when user's sight focuses on anchor point, send the first hint instructions carrying out IMAQ action to IMAQ and memory module;
IMAQ and memory module are used for, and according to the move mode pre-set, tell how user is when holding head position is constant, move mobile terminal, send the second hint instructions to display interface module; According to the first hint instructions sent out from webcam driver module, the facial zone of user is sampled, and preserve the corresponding relation of the first picture and the second picture; When camera is opened, the user's face-image collected is identified, identify the corresponding relation that current user preserves the first picture and the second picture, mate and find the second corresponding picture; Second picture is sent to display interface module; By current sample to the coordinate range of image of user send to display interface module.
Alternatively, described second processing unit comprises display interface module, and communication interface modules; Wherein,
Display interface module is used for: according to the second hint instructions from described IMAQ and memory module, on screen display reminding user this how to move the information of mobile terminal; When camera is opened, according to the 3rd hint instructions from described IMAQ and memory module, with receive second picture replace current sample to user image coordinate range in image and show.
Alternatively, described second processing unit also comprises: communication interface modules;
Described IMAQ and memory module also for: by described, second picture is sent to communication interface modules; By current sample to the coordinate range of image of user send to communication interface modules;
Communication interface modules is used for: when camera is opened, according to the 3rd hint instructions from described IMAQ and memory module, replace the image in the coordinate range of the image of the user that present sample arrives with described the second picture received, then be sent on network after carrying out compressed encoding.
Alternatively, when carrying out described picture and replacing, the image of the eyeball between the upper lower eyelid utilizing the image of the eyeball between the upper lower eyelid in described second picture to replace in described current picture.
Compared with prior art, technical scheme to comprise in advance on record move terminal screen respectively in different anchor point region after conventional direct one's eyes downward the first picture and view angle correction seen between the second picture corresponding relation; Carrying out in video communication, when detecting that current picture mates with the first picture in certain anchor point region, the second picture utilizing this first picture corresponding replaces current picture.Utilize the picture after the view angle correction recorded when the position of camera is overlapping with this anchor point, replace the current picture in live video communication, correct current video communication picture video communicating pair visual angle, improve video communication quality, and then improve Consumer's Experience.
Other features and advantages of the present invention will be set forth in the following description, and, partly become apparent from specification, or understand by implementing the present invention.Object of the present invention and other advantages realize by structure specifically noted in specification, claims and accompanying drawing and obtain.
Accompanying drawing explanation
Accompanying drawing described herein is used to provide a further understanding of the present invention, and form a application's part, schematic description and description of the present invention, for explaining the present invention, does not form inappropriate limitation of the present invention.In the accompanying drawings:
Fig. 1 is the flow chart that the present invention realizes the method for video communication;
Fig. 2 is the schematic diagram of an embodiment of the anchor point that the screen of mobile phone of the present invention shows;
When Fig. 3 is cell phone of the present invention, the schematic diagram of a display reminding how embodiment of movement;
When Fig. 4 is cell phone of the present invention, how to provide the schematic diagram of an embodiment of correct information;
Fig. 5 is the schematic diagram of imaging embodiment of the present invention;
Fig. 6 is the device schematic diagram of auxiliary moving mobile phone of the present invention;
Fig. 7 is the composition structural representation that the present invention realizes the device of video communication.
Embodiment
For making the object, technical solutions and advantages of the present invention clearly understand, hereinafter will be described in detail to embodiments of the invention by reference to the accompanying drawings.It should be noted that, when not conflicting, the embodiment in the application and the feature in embodiment can combination in any mutually.
Fig. 1 is the flow chart that the present invention realizes the method for video communication, as shown in Figure 1, comprising:
Step 100: distinguish the corresponding relation on record move terminal screen in different anchor point region between the first picture and the second picture in advance.
Also comprise before this step: obtain the first picture, specifically comprise:
Pre-set several anchor points (such as shielding background in vain, the point of black location) on the screen of the mobile terminal, keep user's face constant with mobile phone relative position.Screen shows anchor point successively, and for each anchor point, user's sight focuses on the stain of location, as by continuous nictation as 2 times, keeping certain duration as 1 second for another example, representing to have completed and watching this anchor point attentively by watching this anchor point attentively.System, after user has completed and watches this anchor point attentively, records current picture as the first picture.Like this until whole anchor point has shown, and till completing the first picture recording all anchor points.
Also comprise before this step: obtain the second picture, specifically comprise:
According to the move mode pre-set, display reminding information on screen, to tell that user is when holding head position is constant, how to move mobile terminal, such as: can be that show in the mode of arrow should the direction of movement and position, as arrow length represents the distance of movement, arrow points represents the direction of movement, word and digital prompt can also be aided with simultaneously, such as show the numerical value of the distance length of movement.This object moving mobile terminal according to predetermined manner is that camera is corresponding overlapping one by one with (three dimensions) position of the anchor point previously shown on screen, and is often locating on overlapping position, records current picture as the second picture.
It should be noted that, the acquisition of the first picture and the second picture can order in no particular order, as long as corresponding each anchor point obtains corresponding different pictures.
Like this, after the first picture of each anchor point of all correspondences and the second picture record complete, form the one-to-one relationship between the first picture and the second picture in different anchor point region, namely any one anchor point on screen has recorded the picture (i.e. the first picture) seen of directing one's eyes downward of the routine on this anchor point all respectively, forms man-to-man corresponding relation with the picture (the second picture) after the view angle correction recorded when the position of camera is overlapping with this anchor point.
It should be noted that, the density chosen when anchor point is enough large, can cover points all on whole screen, the track of mode record current user's pupil movement that (video) continuously such as can be adopted to make a video recording, thus covers whole screen.
Corresponding each anchor point, can record the first picture of different user and the corresponding relation of the second picture respectively.
Step 101: carrying out in video communication, when detecting that current picture mates with the first picture in certain anchor point region, the second picture utilizing this first picture corresponding replaces current picture.
In this step, when user carries out video communication, if detect that the picture of current video communication mates as the most close with the first picture of certain anchor point record, corresponding relation then by setting up, find second picture corresponding with this anchor point, and utilize this second picture to replace the picture of current video communication.It should be noted that, specifically how to realize the conventional techniques means judgement whether picture mates being belonged to those skilled in the art, the protection range be not intended to limit the present invention, repeats no more here.
If the position display of this anchor point on screen is the eyes (or article on nose or ear or picture background) of the opposite end participating in communication, so, by method of the present invention, the user of Correspondent Node just can feel that this user looking at the eyes (or article on nose or ear or picture background) of oneself.
Preferably, when carrying out picture and replacing, only can replace the image of the eyeball between upper lower eyelid, ensure that other the real life facial expression of the picture of current video communication so better.Specifically how to realize the conventional techniques the means only replacement of ball portions image being belonged to those skilled in the art, the protection range be not intended to limit the present invention, repeats no more here.
If corresponding each anchor point, when preserving the corresponding relation of multiple user, in the process of video calling, before this step of execution, also comprise: identifying current by facial characteristics is which user uses mobile terminal, and then according to recognition result, choose the second corresponding picture and carry out replacing.Specifically how to identify the current conventional techniques means being which user and belonging to those skilled in the art by facial characteristics, the protection range be not intended to limit the present invention, repeats no more here.
Further, if recognition result is the corresponding relation that active user does not have in pre-recorded step 100, so the inventive method is exited.
Because mobile terminal is personal device, for the consideration of fail safe, before carrying out the corresponding relation in establishment step 100, further, the method also comprises: input password, to guarantee only having owner (or its user authorized) could use this function.
By technical scheme provided by the invention, utilize the picture after the view angle correction recorded when the position of camera is overlapping with this anchor point, replace the current picture in live video communication, correct current video communication picture video communicating pair visual angle, improve video communication quality, and then improve Consumer's Experience.
Below in conjunction with instantiation, take mobile terminal as mobile phone for example is specifically described the inventive method.
When user uses video communication function provided by the invention first, first system points out user to carry out Initialize installation.Now on the screen of mobile phone, demonstrate anchor point.Fig. 2 is the schematic diagram of an embodiment of the anchor point that the screen of mobile phone of the present invention shows, as shown in Figure 2, these anchor points are be set in advance in mobile phone intrasystem, and each anchor point is relative to (three dimensions) relative position of camera, be also be set in advance in intrasystem.
Anchor point shown in Fig. 2 can show one by one; Certainly, also only can show an anchor point, and this anchor point moves according to the track pre-set, to cover the position of all anchor points.
When cell phone, system calculates relative (three dimensions) distance (specific implementation see below to the analysis of Fig. 5) between camera current location and each anchor point automatically, and on screen display reminding information.When Fig. 3 is cell phone of the present invention, the schematic diagram of a display reminding how embodiment of movement, as shown in Figure 3, whenever the location overlap of the position of camera and certain anchor point, display " OK " printed words, now user looks at camera straight, and namely system records current (user's) second picture.When cell phone, no longer show anchor point, but how display reminding moves, and whether move into place.As shown in Figure 3, during user's cell phone, system, according to the facial characteristics of user, carries out area sampling, and calculate current phone motion track in three dimensions, generally using profile visibility points such as the eyes of user or faces as resample area.
When Fig. 4 is cell phone of the present invention, how to provide the schematic diagram of an embodiment of correct information, Fig. 5 is the schematic diagram of imaging embodiment of the present invention, the size of the basic photosensitive unit of photo-sensitive cell is fixing, and the quantity of the basic photosensitive unit that system takies during imaging on photo-sensitive cell according to sampling sample calculates the two-dimensional geometry size (length and width etc.) of the imaging of sampling sample on photo-sensitive cell automatically.For the edge of imaging, as long as this edge occupies certain basic photosensitive unit, then calculate the whole size of this basic photosensitive unit, namely basic photosensitive unit is of a size of minimum of computation precision unit.
As shown in Figure 4 and Figure 5, for the height h of imaging, can the height H of calculating sampling sample itself according to the height h of imaging, i.e. H=h × f/ (d-f), wherein, d is the distance of set of lenses centre distance photo-sensitive cell, the focal length of formation when f is set of lenses to carry out auto-focusing to sample blur-free imaging.Like this, just can when f remain unchanged, by the sampling displacement of sample on photo-sensitive cell (y-axis displacement h', and x-axis displacement w'), calculate the relative displacement (y-axis displacement H', and x-axis displacement W') of sampling sample relative to set of lenses.In like manner can obtain H'=h' × f/ (d-f), and W'=w' × f/ (d-f).
After calculating H, sampling sample distance set of lenses distance D, i.e. D=d × H/h.So just can calculate the distance D (z-axis coordinate) of sampling sample distance set of lenses at any time.
Wherein w', h' answer level or vertical cell phone for decision, and D is for determining whether current phone distance user face keeps relative distance constant.
Comprehensive above-mentioned calculating, just can learn the three-dimensional space position of sampling sample relative to set of lenses, so system now can demonstrate correct information on the display screen, to help user in the mode by means of only handheld mobile phone, the process of successively each anchor point on mobile phone screen being carried out to picture record can be realized.
In addition, conveniently operate, the present invention can also provide aid to user, namely can be a piece of paper matter card, and the pattern on card is the device schematic diagram of auxiliary moving mobile phone of the present invention see Fig. 6, Fig. 6.As shown in Figure 6, this card is pasted on the wall or lies on desk, or on a support leaned to; Mobile phone is placed on card according to the mark overlap on card by user, and according to the mark on card, the position of cell phone can carry out the record of picture easily successively.
Fig. 7 is the composition structural representation that the present invention realizes the device of video communication, as shown in Figure 7, at least comprises the first processing unit, the second processing unit; Wherein,
First processing unit, for the corresponding relation in advance respectively on record move terminal screen in different anchor point region between the first picture and the second picture;
Second processing unit, for carrying out in video communication, when detecting that current picture mates with the first picture in certain anchor point region, the second picture utilizing this first picture corresponding replaces current picture;
Wherein, the first picture is the conventional picture seen of directing one's eyes downward; Second picture is the picture after view angle correction.
First processing module also for: obtain the first picture, the second picture.
Particularly,
First processing unit comprises webcam driver module, and IMAQ and memory module; Wherein,
Webcam driver module for: user's sight focuses on anchor point, sends the first hint instructions carrying out IMAQ action to IMAQ and memory module.Particularly: the hardware parameter reading camera, as shown in Figure 4 and Figure 5, mainly comprise the distance d of set of lenses centre distance photo-sensitive cell, the focal distance f of rear formation of at every turn having focused, the physical picture element number of photo-sensitive cell, the physical size (long and wide) etc. of single pixel; Two dimension numbering (x, y) is carried out to each pixel.Identify the actions such as the nictation that user makes, and send the first hint instructions carrying out IMAQ action to IMAQ and memory module.
IMAQ and memory module are used for: according to the move mode pre-set, and tell how user is when holding head position is constant, move mobile terminal, and send the second hint instructions to display interface module.Particularly: feature extraction (such as extracting face four canthus, the border between upper lower lip, the region of the position formation that the borders such as two corners of the mouths are relatively sharp keen) is carried out to the image photographed (static or video) at every turn; As shown in Figure 4 and Figure 5, the numbering of actual physical picture element (on x and y two coordinates) number that takies of resample area and the pixel shared by resample area border is calculated; Calculate height h (y coordinate dimension) and the width w (x coordinate dimension) of resample area imaging on photo-sensitive cell, thus draw H, and when the imaging of resample area changes, calculate the difference of pixel number on photo-sensitive cell, thus draw h', w'; D is calculated according to d, H, h.According to h', w' and D, send the second hint instructions to display interface module;
According to the first hint instructions sent out from webcam driver module, to the face of user, can only sample to ocular especially, and the corresponding relation that namely corresponding relation preserving the first picture and the second picture samples with current anchor point or camera; Further, the first picture is ocular image A, and the second picture is ocular image B is example, also for distinguishing different users, preserves many groups of (ocular image A
locating point position) and (ocular image B
camera position) the corresponding relation i.e. corresponding relation of the first picture and the second picture; (the locating point position that saved system is built-in
camera position) one group of corresponding relation;
When camera is opened, the user's face-image collected is identified, identify current user and whether preserve (ocular image A
locating point position) and (ocular image B
camera position) the corresponding relation i.e. corresponding relation of the first picture and the second picture, if preserved, the image of the user's ocular then arrived according to current sample, search coupling as the most close ocular image A, and according to: the corresponding relation of ocular image A → locating point position → camera position → ocular image B, finds corresponding ocular image B; Ocular image B is sent to display interface module in real time; The coordinate range of the image of the user simultaneously also arrived by current sample, the coordinate range that can be the image of ocular especially sends to display interface module in real time.
Second processing unit at least comprises display interface module, for: according to the second hint instructions from IMAQ and memory module, using h', w' and D as parameter, display reminding information on screen.This how cell phone of prompting user, to position the three-dimensional space position collecting camera, to show anchor point on screen;
When camera is opened, if the image information collected is shown on the display screen of current phone the machine, then according to the 3rd hint instructions from IMAQ and memory module, with the ocular image B received replace current sample to user's ocular image coordinate range in (in display-memory) image (data) being shown to receive on mobile phone screen.
Further, the second processing module also comprises communication interface modules; Now,
Institute's IMAQ and memory module also for: by described, second picture is sent to communication interface modules; By current sample to the coordinate range of image of user send to communication interface modules
Communication interface modules is used for: when camera is opened, if the image information collected is sent on network, such as carry out video communication, so, according to the 3rd hint instructions from IMAQ and memory module, in the coordinate range of the image of the user's ocular arrived with the ocular image B replacement current sample received (send the compressed encoding in buffer memory at network before) image (data), carry out compressed encoding again after replacing it and be sent on network.
Especially, usually when carrying out video communication, the process of communication interface modules and display interface module is simultaneous.
The above, be only preferred embodiments of the present invention, be not intended to limit protection scope of the present invention.Within the spirit and principles in the present invention all, any amendment made, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (15)
1. realize a method for video communication, it is characterized in that, comprising: distinguish the corresponding relation on record move terminal screen in different anchor point region between the first picture and the second picture in advance;
Carrying out in video communication, when detecting that current picture mates with the first picture in certain anchor point region, the second picture utilizing this first picture corresponding replaces current picture;
Wherein, the first picture is the conventional picture seen of directing one's eyes downward; Second picture is the picture after view angle correction.
2. method according to claim 1, is characterized in that, also comprises before the method: obtain described first picture.
3. method according to claim 2, is characterized in that, the screen of described mobile terminal pre-sets several anchor points; Described first picture of described acquisition comprises:
Keep user's face constant with described mobile terminal relative position; Screen shows anchor point successively, and for each anchor point, user's sight focuses on anchor point, and records current picture as described first picture.
4. method according to claim 1, is characterized in that, also comprises before the method: obtain described second picture.
5. method according to claim 4, is characterized in that, described acquisition second picture comprises:
According to the move mode pre-set, display reminding information on screen, to tell that user is when holding head position is constant, how to move mobile terminal, to make camera and the position at described each anchor point corresponding overlapping one by one, and often locating on overlapping position, record current picture is as described second picture.
6. the method according to any one of Claims 1 to 5, is characterized in that, described each anchor point records first picture of one or more users and the corresponding relation of the second picture respectively.
7. method according to claim 1, is characterized in that, described current picture mates with the first picture in certain anchor point region and is: the picture of described current video communication is the most close with the first picture of certain anchor point record.
8. the method according to claim 1 or 7, is characterized in that, when carrying out described picture and replacing, and the image of the eyeball between the upper lower eyelid utilizing the image of the eyeball between the upper lower eyelid in described second picture to replace in described current picture.
9. method according to claim 6, is characterized in that, when described each anchor point preserves the corresponding relation of two or more users, in the process of described video calling, before the described replacement current picture of execution, also comprises:
Identify the user in current video call by facial characteristics, according to recognition result, choose second picture of user carrying out described replacement.
10. realize a device for video communication, it is characterized in that, at least comprise the first processing unit, the second processing unit; Wherein,
First processing unit, for the corresponding relation in advance respectively on record move terminal screen in different anchor point region between the first picture and the second picture;
Second processing unit, for carrying out in video communication, when detecting that current picture mates with the first picture in certain anchor point region, the second picture utilizing this first picture corresponding replaces current picture;
Wherein, the first picture is the conventional picture seen of directing one's eyes downward; Second picture is the picture after view angle correction.
11. devices according to claim 10, is characterized in that, described first processing module also for: obtain described first picture and described second picture.
12. devices according to claim 10 or 11, it is characterized in that, described first processing unit comprises webcam driver module, and IMAQ and memory module; Wherein,
Webcam driver module for: when user's sight focuses on anchor point, send the first hint instructions carrying out IMAQ action to IMAQ and memory module;
IMAQ and memory module are used for, and according to the move mode pre-set, tell how user is when holding head position is constant, move mobile terminal, send the second hint instructions to display interface module; According to the first hint instructions sent out from webcam driver module, the facial zone of user is sampled, and preserve the corresponding relation of the first picture and the second picture; When camera is opened, the user's face-image collected is identified, identify the corresponding relation that current user preserves the first picture and the second picture, mate and find the second corresponding picture; Second picture is sent to display interface module; By current sample to the coordinate range of image of user send to display interface module.
13. devices according to claim 12, is characterized in that, described second processing unit comprises display interface module, and communication interface modules; Wherein,
Display interface module is used for: according to the second hint instructions from described IMAQ and memory module, on screen display reminding user this how to move the information of mobile terminal; When camera is opened, according to the 3rd hint instructions from described IMAQ and memory module, with receive second picture replace current sample to user image coordinate range in image and show.
14. devices according to claim 13, is characterized in that, described second processing unit also comprises: communication interface modules;
Described IMAQ and memory module also for: by described, second picture is sent to communication interface modules; By current sample to the coordinate range of image of user send to communication interface modules;
Communication interface modules is used for: when camera is opened, according to the 3rd hint instructions from described IMAQ and memory module, replace the image in the coordinate range of the image of the user that present sample arrives with described the second picture received, then be sent on network after carrying out compressed encoding.
15. devices according to claim 10, is characterized in that, when carrying out described picture and replacing, and the image of the eyeball between the upper lower eyelid utilizing the image of the eyeball between the upper lower eyelid in described second picture to replace in described current picture.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510527270.2A CN105049778A (en) | 2015-08-25 | 2015-08-25 | Method and device for realizing video communication |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510527270.2A CN105049778A (en) | 2015-08-25 | 2015-08-25 | Method and device for realizing video communication |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105049778A true CN105049778A (en) | 2015-11-11 |
Family
ID=54455933
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510527270.2A Pending CN105049778A (en) | 2015-08-25 | 2015-08-25 | Method and device for realizing video communication |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105049778A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105812709A (en) * | 2016-03-18 | 2016-07-27 | 合肥联宝信息技术有限公司 | Method for realizing virtual camera by using cameras |
| CN110503911A (en) * | 2019-08-09 | 2019-11-26 | 武汉华星光电半导体显示技术有限公司 | Display panel and electronic equipment |
| WO2020097891A1 (en) * | 2018-11-15 | 2020-05-22 | 李庆远 | Video chat device and method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070230794A1 (en) * | 2006-04-04 | 2007-10-04 | Logitech Europe S.A. | Real-time automatic facial feature replacement |
| CN102483854A (en) * | 2009-09-11 | 2012-05-30 | 皇家飞利浦电子股份有限公司 | Image processing system |
| CN103034330A (en) * | 2012-12-06 | 2013-04-10 | 中国科学院计算技术研究所 | Eye interaction method and system for video conference |
| CN204168406U (en) * | 2014-08-20 | 2015-02-18 | 深圳市融创天下科技有限公司 | A kind of sight line means for correcting for video calling |
-
2015
- 2015-08-25 CN CN201510527270.2A patent/CN105049778A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070230794A1 (en) * | 2006-04-04 | 2007-10-04 | Logitech Europe S.A. | Real-time automatic facial feature replacement |
| CN102483854A (en) * | 2009-09-11 | 2012-05-30 | 皇家飞利浦电子股份有限公司 | Image processing system |
| CN103034330A (en) * | 2012-12-06 | 2013-04-10 | 中国科学院计算技术研究所 | Eye interaction method and system for video conference |
| CN204168406U (en) * | 2014-08-20 | 2015-02-18 | 深圳市融创天下科技有限公司 | A kind of sight line means for correcting for video calling |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105812709A (en) * | 2016-03-18 | 2016-07-27 | 合肥联宝信息技术有限公司 | Method for realizing virtual camera by using cameras |
| WO2020097891A1 (en) * | 2018-11-15 | 2020-05-22 | 李庆远 | Video chat device and method |
| CN110503911A (en) * | 2019-08-09 | 2019-11-26 | 武汉华星光电半导体显示技术有限公司 | Display panel and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105898186B (en) | Display methods and video conferencing system for video conference | |
| US11050915B2 (en) | Method for zooming by switching between dual cameras, mobile terminal, and storage apparatus | |
| CN104685462B (en) | Adaptive thresholding for image identification | |
| JP6165459B2 (en) | Method for correcting user's line of sight in video, machine-readable storage medium, and portable terminal | |
| CN104754216B (en) | A kind of photographic method and device | |
| CN107831904B (en) | Electronic device and operation method thereof | |
| EP3163500A1 (en) | Method and device for identifying region | |
| US20170372449A1 (en) | Smart capturing of whiteboard contents for remote conferencing | |
| CN109684980B (en) | Automatic scoring method and device | |
| CN107771391B (en) | Method and apparatus for determining exposure time of image frame | |
| CN104363377B (en) | Display methods, device and the terminal of focus frame | |
| CN106250831A (en) | Image detecting method, device and the device for image detection | |
| CN103402058B (en) | A kind of processing method and processing device shooting image | |
| CN102867321A (en) | System and method for eyeglasses virtual try-on interactive service | |
| CN102169540B (en) | Camera-based point reading positioning method and device | |
| CN103501411A (en) | Image shooting method and system | |
| CN105049778A (en) | Method and device for realizing video communication | |
| US10692230B2 (en) | Document imaging using depth sensing camera | |
| CN110650284B (en) | Image shooting control method, device, equipment and storage medium | |
| JP6283329B2 (en) | Augmented Reality Object Recognition Device | |
| CN107172383B (en) | A kind of Obj State detection method and device | |
| JP4898655B2 (en) | Imaging apparatus and image composition program | |
| CN115019324A (en) | Interactive method and device for text scanning, computer equipment and storage medium | |
| CN111914785A (en) | Method and device for improving definition of face image and storage medium | |
| CN105306797A (en) | User terminal and image shooting method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151111 |
|
| RJ01 | Rejection of invention patent application after publication |