CN101211463A - Method for automatically converting two-dimension image to three-dimensional image - Google Patents
Method for automatically converting two-dimension image to three-dimensional image Download PDFInfo
- Publication number
- CN101211463A CN101211463A CNA2006101721313A CN200610172131A CN101211463A CN 101211463 A CN101211463 A CN 101211463A CN A2006101721313 A CNA2006101721313 A CN A2006101721313A CN 200610172131 A CN200610172131 A CN 200610172131A CN 101211463 A CN101211463 A CN 101211463A
- Authority
- CN
- China
- Prior art keywords
- image
- baseline
- displacement
- conversion method
- centre coordinate
- 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
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000006073 displacement reaction Methods 0.000 claims abstract description 28
- 238000006243 chemical reaction Methods 0.000 claims description 30
- 238000010586 diagram Methods 0.000 description 14
- 230000000007 visual effect Effects 0.000 description 5
- 210000004556 brain Anatomy 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
Images
Landscapes
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a method for converting a 2D image into a 3D image, which comprises the following steps: (a) confining an object in the 2D image; (b) setting a base line in the 2D image; (c) judging a foreground or background of an object bit in the 2D image according to the base line; (d) giving a displacement for the object; (e) moving the object according to the displacement so as to generate a plurality of continuous images; and (f) outputting each of the continuous images in sequence so as to generate the 3D image. Therefore, the method of the invention can automatically convert the 2D image into the 3D image after the user confines the object in the 2D image.
Description
Technical field
The present invention is about a kind of image conversion method, and particularly about a kind of can be the method for 3D (three-dimensional) image with 2D (two dimension) video conversion automatically.
Background technology
Generally speaking, the 3D image all is made up of the image information of two groups of different visual angles, and wherein, one group corresponding to the left eye visual angle, and another is organized then corresponding to the right eye visual angle.When playing the 3D image, observer's left eye only can be seen the image information corresponding to the left eye visual angle, and right eye only can be seen the image information corresponding to the right eye visual angle, and whereby, the observer promptly can produce stereoscopic vision in brain.
At present, existing prior art can be the 3D image with the 2D video conversion.In the prior art, when user's desire is the 3D image with the 2D video conversion, it must select at least one object (Object) at 2D image centre circle earlier.Then, by the user judge voluntarily this enclosed choosing to as if belong to the prospect (Foreground) or the background (Background) of 2D image.Afterwards, the user decides this how much depth of field of object that gives to be enclosed choosing (Depth of field) again in its sole discretion.If the object by the circle choosing is more than two, then the user must do the adjustment of above-mentioned steps respectively to each object.This is quite inconvenient concerning the user.
Therefore, it can be the method for 3D image with the 2D video conversion automatically that category of the present invention is to provide a kind of, to address the above problem.
Summary of the invention
One of category of the present invention is to provide a kind of image conversion method, when the user 2D image centre circle select desire to be converted to the object of 3D image after, the present invention can judge automatically that each object of circle choosing belongs to prospect or background, and give each object the corresponding depth of field automatically, and then form the 3D image.
According to a preferred specific embodiment, image conversion method of the present invention is in order to being the 3D image with the 2D video conversion, and this method comprises the following steps.At first, in the 2D image, circle selects at least one object, and in the 2D image, sets baseline (Base line).Then, according to baseline, judge prospect or the background of each object position in the 2D image, wherein, N first object is positioned at prospect, and M second object is positioned at background, and N and M are more than or equal to 0 integer and are not 0 simultaneously.Afterwards, respectively with each N first object and each M second object order, and, give each N first object, first displacement respectively according to the ordering of N first object, and, give each M second object, second displacement respectively according to the ordering of M second object.Move each N first object according to first displacement, and move each M second object according to second displacement, open continuous image to produce T, T is a natural number.At last, export each T in regular turn and open continuous image, to produce the 3D image.
Whereby, when the user after 2D image centre circle has selected object, method of the present invention can be the 3D image with the 2D video conversion automatically.For the user, very convenient.
Can be further understood by the following detailed description and accompanying drawings about the advantages and spirit of the present invention.
Description of drawings
Figure 1 shows that the synoptic diagram of 2D image.
Figure 2 shows that desk is enclosed the synoptic diagram of choosing among Fig. 1.
Fig. 3 A to Fig. 3 E is depicted as the synoptic diagram about five continuous images of desk among Fig. 2.
Figure 4 shows that among Fig. 1 that desk and chair are enclosed the synoptic diagram of choosing.
Fig. 5 A to Fig. 5 E is depicted as the synoptic diagram about five continuous images of desk among Fig. 4 and chair.
Figure 6 shows that among Fig. 1 that desk and chair are enclosed the synoptic diagram of choosing.
Fig. 7 A to Fig. 7 E is depicted as the synoptic diagram about five continuous images of desk among Fig. 6 and chair.
The primary clustering symbol description
1:2D image 10: desk (object)
12,14,16: chair (object) 18: piano (object)
Y1, Y1 ', Y1 ": baseline d, d1, d2, d3: displacement
C (x, y), C1 (x1, y1), C2 (x2, y2), C3 (x3, y3): centre coordinate
I1-I5, I1 '-I5 ', I1 " I5 ": continuous image
A1: first direction A2: second direction
Embodiment
Image conversion method of the present invention is in order to being the 3D image with the 2D video conversion.See also Fig. 1, Figure 1 shows that the synoptic diagram of 2D image 1.As shown in Figure 1, comprise a plurality of objects in the 2D image 1, as desk 10, chair 12,14,16, piano 18 etc.For reaching above-mentioned relevant category of the present invention, technological means that is adopted and complementary work thereof are imitated, and now lift several preferred specific embodiments and are illustrated as follows:
The first preferred specific embodiment:
The first preferred specific embodiment illustrates that image conversion method of the present invention is in order to be converted to the desk in the 2D image 10 action principle of 3D image.
See also Fig. 1 to Fig. 3 E, Figure 2 shows that desk 10 is by the synoptic diagram of circle choosing among Fig. 1, Fig. 3 A to Fig. 3 E is depicted as the synoptic diagram about five continuous images of desk among Fig. 2 10.
In this embodiment, at first, the user needs in 2D image 1, and circle selects desk 10 (being represented by dotted lines), and in 2D image 1, sets baseline Y1.In this embodiment, baseline Y1 is a horizontal line.
Then, calculate desk 10 centre coordinate C (x, y), and according to centre coordinate C (x y) with respect to the position of baseline Y1, judges that desk 10 is arranged in the prospect or the background of 2D image 1.As shown in Figure 2, because the y coordinate of centre coordinate C is positioned under the baseline Y1, therefore judge that desk 10 is arranged in the prospect of 2D image 1.In this embodiment, (x is to calculate and get via following formula one y) to centre coordinate C.
Formula one: C (x, y)=(sum (x)/n, sum (y)/n).
In formula one, n represents the quantity of all pixels in the desk 10, and sum (x) represents the x coordinate summation of each pixel, and sum (y) represents the y coordinate summation of each pixel.
Afterwards, give desk 10 displacement d, and according to the centre coordinate C of desk 10, with desk 10 towards first direction (in Fig. 3 A to Fig. 3 E, the direction of arrow A 1) mobile displacement d five times in regular turn, to produce five continuous image I1-I5, shown in Fig. 3 A to Fig. 3 E.At last, export each continuous image I1-I5 in regular turn, to produce the 3D image of desk 10.
The second preferred specific embodiment:
The second preferred specific embodiment illustrates that image conversion method of the present invention is in order to be converted to the desk in the 2D image 10 and chair 12 action principle of 3D image.
See also Fig. 1 and Fig. 4 to Fig. 5 E, Figure 4 shows that desk 10 among Fig. 1 and chair 12 by the synoptic diagram of circle choosing, Fig. 5 A to Fig. 5 E is depicted as the synoptic diagram about five continuous images of desk among Fig. 4 10 and chair 12.
In this embodiment, at first, the user needs in 2D image 1, and circle selects desk 10 and chair 12 (being represented by dotted lines), and in 2D image 1, sets baseline Y1 '.In this embodiment, baseline Y1 ' is a horizontal line.
Then, calculate desk 10 centre coordinate C1 (x1, y1) and the centre coordinate C2 (x2 of chair 12, y2), and according to centre coordinate C1 (x1, y1) and C2 (x2, y2), judge that desk 10 and chair 12 are arranged in the prospect or the background of 2D image 1 with respect to the position of baseline Y1 '.As shown in Figure 4, because y coordinate y1, the y2 of centre coordinate C1, C2 all are positioned under the baseline Y1 ', therefore judge that desk 10 and chair 12 are arranged in the prospect of 2D image 1.
Afterwards, with desk 10 and chair 12 orderings.In this embodiment, the foundation of ordering is: (1) if the centre coordinate of object is far away apart from baseline, then the ordering of object is than the front; (2) if extend upward liking from the bottom of 2D image 1, then the ordering of object is than the front; (3), then enclosed the ordering of the object that selects earlier than the front if the centre coordinate of two objects is identical with respect to the distance of baseline.Therefore, the ordering of chair 12 is before desk 10.
Then, give desk 10 displacement d1, and centre coordinate C1 according to desk 10, towards first direction (in Fig. 5 A to Fig. 5 E, the direction of arrow A 1) mobile displacement d1 five times in regular turn, give chair 12 displacement d2 on desk 10, and centre coordinate C2 according to chair 12, with chair 12 towards first direction mobile displacement d2 five times in regular turn, to produce five continuous image I1 '-I5 ', shown in Fig. 5 A to Fig. 5 E.At last, export each continuous image I1 '-I5 ' in regular turn, to produce the 3D image of desk 10 and chair 12.
The 3rd preferred specific embodiment:
The 3rd preferred specific embodiment illustrates that image conversion method of the present invention is in order to be converted to the desk in the 2D image 10 and chair 16 action principle of 3D image.
See also Fig. 1 and Fig. 6 to Fig. 7 E, Figure 6 shows that desk 10 among Fig. 1 and chair 16 by the synoptic diagram of circle choosing, Fig. 7 A to Fig. 7 E is depicted as the synoptic diagram about five continuous images of desk among Fig. 6 10 and chair 16.
In this embodiment, at first, the user needs in 2D image 1, and circle selects desk 10 and chair 16 (being represented by dotted lines), and in 2D image 1, sets baseline Y1 ".In this embodiment, baseline Y1 " is a horizontal line.
Then, calculate desk 10 centre coordinate C1 (x1, y1) and the centre coordinate C3 (x3 of chair 16, y3), and according to centre coordinate C1 (x1, y1) and C3 (x3, y3) with respect to baseline Y1 " the position, judge that desk 10 and chair 16 are arranged in the prospect or the background of 2D image 1.As shown in Figure 6, because the y coordinate y1 of centre coordinate C1 is positioned at baseline Y1 " under, therefore judge that desk 10 is arranged in the prospect of 2D image 1; Because the y coordinate y3 of centre coordinate C3 is positioned at baseline Y1 " on, therefore judge that chair 16 is arranged in the background of 2D image 1.
Afterwards, give desk 10 displacement d1, and according to the centre coordinate C1 of desk 10, with desk 10 towards first direction (in Fig. 7 A to Fig. 7 E, the direction of arrow A 1) mobile displacement d1 five times in regular turn, give chair 16 displacement d3, and according to the centre coordinate C3 of chair 16, with chair 16 towards second direction (in Fig. 7 A to Fig. 7 E, the direction of arrow A 2) mobile displacement d3 five times in regular turn, to produce five continuous image I1 " I5 ", shown in Fig. 7 A to Fig. 7 E.At last, export each continuous image I1 " I5 " in regular turn, to produce the 3D image of desk 10 and chair 16.First direction and second direction are reverse.
Be noted that the quantity of above-mentioned displacement and the last continuous image that produces all can be designed according to practical application by the deviser.Whereby, the present invention can be applicable to various 3D displays, as inclined lens pillar (Slanted lenticular), straight formula lens pillar, polaroid form etc.If the 3D display is the polaroid form, at last as long as produce two continuous images.
Compared to prior art, when the user after 2D image centre circle has selected object, method of the present invention can be the 3D image with the 2D video conversion automatically.For the user, very convenient.
By the detailed description of above preferred specific embodiment, hope can be known description feature of the present invention and spirit more, and is not to come category of the present invention is limited with above-mentioned disclosed preferred specific embodiment.On the contrary, its objective is that hope can contain in the category of claim of being arranged in of various changes and tool equality institute of the present invention desire application.Therefore, category of the present invention should be done the broadest explanation according to above-mentioned explanation, contains the arrangement of all possible change and tool equality to cause it.
Claims (11)
1. image conversion method, in order to be a 3D image with a 2D video conversion, this image conversion method comprises the following steps:
(a) in this 2D image, circle selects at least one object (Object);
(b) in this 2D image, set a baseline (Base line);
(c) according to this baseline, judge a prospect (Foreground) or the background (Background) of each object position in this 2D image, wherein, N first object is positioned at this prospect, M second object is positioned at this background, and N and M are one more than or equal to 0 integer and be not 0 simultaneously;
(d) respectively with each N first object and each M second object order;
(e), give each N first object, one first displacement respectively, and, give each M second object, one second displacement respectively according to the ordering of this M second object according to the ordering of this N first object;
(f) move each N first object according to this first displacement, and move each M second object according to this second displacement, open continuous image to produce T, T is a natural number; And
(g) export each T in regular turn and open continuous image, to produce this 3D image.
2. image conversion method according to claim 1, wherein step (c) also comprises the following steps:
(c1) calculate a centre coordinate of each object; And
(c2) according to this centre coordinate of each object position, judge that each object is arranged in this prospect or this background of this 2D image with respect to this baseline.
3. image conversion method according to claim 2, wherein in step (d), if this centre coordinate of one of them of this at least one object is far away apart from this baseline, then the ordering of this object is than the front.
4. image conversion method according to claim 3 wherein in step (d), extends upward if one of them of this at least one object is a bottom from this 2D image, and then the ordering of this object is than the front.
5. image conversion method according to claim 4 wherein in step (d), if this centre coordinate of two objects is identical with respect to the distance of this baseline, is then enclosed the ordering of this object that selects earlier than the front.
6. image conversion method according to claim 2, wherein in step (f), this centre coordinate according to this first object, this first object is moved this first displacement T time in regular turn towards a first direction, and this centre coordinate according to this second object, this second object is moved this second displacement T time in regular turn towards a second direction, open continuous image to produce this T, this first direction and this second direction are reverse.
7. image conversion method according to claim 1, wherein this baseline is a horizontal line.
8. image conversion method, in order to be a 3D image with a 2D video conversion, this image conversion method comprises the following steps:
(a) in this 2D image, circle selects an object;
(b) in this 2D image, set a baseline;
(c), judge that this object is arranged in a prospect or a background of this 2D image according to this baseline;
(d) give this object one displacement;
(e) move this object according to this displacement, open continuous image to produce T, T is a natural number; And
(f) export each T in regular turn and open continuous image, to produce this 3D image.
9. image conversion method according to claim 8, wherein step (c) also comprises the following steps:
(c1) calculate a centre coordinate of this object; And
(c2) according to this centre coordinate of this object position, judge that this object is arranged in this prospect or this background of this 2D image with respect to this baseline.
10. image conversion method according to claim 9, wherein in step (e), if this object is arranged in this prospect of this 2D image, according to this centre coordinate of this object, this object is moved this displacement T time in regular turn towards a first direction, open continuous image to produce this T; If this object is arranged in this background of this 2D image, according to this centre coordinate of this object, this object is moved this displacement T time in regular turn towards a second direction, open continuous image to produce this T, this first direction and this second direction are reverse.
11. image conversion method according to claim 8, wherein this baseline is a horizontal line.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNB2006101721313A CN100552719C (en) | 2006-12-27 | 2006-12-27 | Can automatically bidimensional image be converted to the method for 3-dimensional image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNB2006101721313A CN100552719C (en) | 2006-12-27 | 2006-12-27 | Can automatically bidimensional image be converted to the method for 3-dimensional image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN101211463A true CN101211463A (en) | 2008-07-02 |
CN100552719C CN100552719C (en) | 2009-10-21 |
Family
ID=39611469
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CNB2006101721313A Expired - Fee Related CN100552719C (en) | 2006-12-27 | 2006-12-27 | Can automatically bidimensional image be converted to the method for 3-dimensional image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN100552719C (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101917636A (en) * | 2010-04-13 | 2010-12-15 | 上海易维视科技有限公司 | Method and system for converting two-dimensional video of complex scene into three-dimensional video |
CN107845059A (en) * | 2017-10-12 | 2018-03-27 | 北京宇航时代科技发展有限公司 | Human meridian point's state dynamically normalized digital analysis system and method |
CN109791703A (en) * | 2017-08-22 | 2019-05-21 | 腾讯科技(深圳)有限公司 | Three dimensional user experience is generated based on two-dimensional medium content |
-
2006
- 2006-12-27 CN CNB2006101721313A patent/CN100552719C/en not_active Expired - Fee Related
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101917636A (en) * | 2010-04-13 | 2010-12-15 | 上海易维视科技有限公司 | Method and system for converting two-dimensional video of complex scene into three-dimensional video |
CN109791703A (en) * | 2017-08-22 | 2019-05-21 | 腾讯科技(深圳)有限公司 | Three dimensional user experience is generated based on two-dimensional medium content |
CN107845059A (en) * | 2017-10-12 | 2018-03-27 | 北京宇航时代科技发展有限公司 | Human meridian point's state dynamically normalized digital analysis system and method |
Also Published As
Publication number | Publication date |
---|---|
CN100552719C (en) | 2009-10-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9438878B2 (en) | Method of converting 2D video to 3D video using 3D object models | |
CN100483463C (en) | System and method for rendering 3-D images on a 3-d image display screen | |
CN104023220B (en) | Real-time multi views synthesizer | |
US6515663B1 (en) | Apparatus for and method of processing three-dimensional images | |
CN101930620B (en) | Image processing method and associated apparatus for rendering three-dimensional effect using two-dimensional image | |
CN108513123B (en) | Image array generation method for integrated imaging light field display | |
US5953014A (en) | Image generation using three z-buffers | |
CN101189643A (en) | 3D image forming and displaying system | |
US10855965B1 (en) | Dynamic multi-view rendering for autostereoscopic displays by generating reduced number of views for less-critical segments based on saliency/depth/eye gaze map | |
CN104081768B (en) | Different visual point image generating means and different visual point image generating method | |
CN102783162A (en) | Image capture device | |
CN101236662A (en) | Apparatus and method for generating CG image for 3-D display | |
JPH11511316A (en) | 3D image display drive | |
CN106412556B (en) | A kind of image generating method and device | |
CN103974055A (en) | 3D photo creation system and method | |
CN102447934A (en) | Synthetic method of stereoscopic elements in combined stereoscopic image system collected by sparse lens | |
CN109934933A (en) | Emulation mode based on virtual reality and the image simulation system based on virtual reality | |
WO2017128887A1 (en) | Method and system for corrected 3d display of panoramic image and device | |
US20080143716A1 (en) | Method capable of automatically transforming 2D image into 3D image | |
CN102510515A (en) | Grating-type multi-viewpoint stereo image synthesis method | |
CN102708577A (en) | Method for synthesizing multi-view-point three-dimensional picture | |
CN100552719C (en) | Can automatically bidimensional image be converted to the method for 3-dimensional image | |
CN107038749A (en) | Three-dimensional Multi-resolution modeling method and model building device | |
CN103632390A (en) | Method for realizing naked eye 3D (three dimensional) animation real-time making by using D3D (Direct three dimensional) technology | |
CN100369062C (en) | Method for forming three-dimensional image and its display system |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20091021 |