CN108683865A - A kind of background replacement system and method for bullet time special efficacy - Google Patents
A kind of background replacement system and method for bullet time special efficacy Download PDFInfo
- Publication number
- CN108683865A CN108683865A CN201810372971.7A CN201810372971A CN108683865A CN 108683865 A CN108683865 A CN 108683865A CN 201810372971 A CN201810372971 A CN 201810372971A CN 108683865 A CN108683865 A CN 108683865A
- Authority
- CN
- China
- Prior art keywords
- image
- foreground
- bullet time
- foreground image
- shade
- 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
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000000926 separation method Methods 0.000 claims abstract description 29
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 24
- 230000000694 effects Effects 0.000 claims abstract description 22
- 238000003786 synthesis reaction Methods 0.000 claims abstract description 15
- 238000006748 scratching Methods 0.000 claims abstract description 4
- 230000002393 scratching effect Effects 0.000 claims abstract description 4
- 238000004519 manufacturing process Methods 0.000 claims description 21
- 240000001973 Ficus microcarpa Species 0.000 claims description 16
- 238000005516 engineering process Methods 0.000 claims description 8
- 230000004075 alteration Effects 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 6
- 230000000750 progressive effect Effects 0.000 claims description 6
- 230000006641 stabilisation Effects 0.000 claims description 6
- 238000011105 stabilization Methods 0.000 claims description 6
- 230000007704 transition Effects 0.000 claims description 5
- 238000009499 grossing Methods 0.000 claims 1
- 239000000284 extract Substances 0.000 description 7
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 6
- 230000000007 visual effect Effects 0.000 description 6
- 230000003068 static effect Effects 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000002955 isolation Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000001151 other effect Effects 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
- H04N5/272—Means for inserting a foreground image in a background image, i.e. inlay, outlay
-
- G06T5/70—
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
- H04N5/265—Mixing
Abstract
A kind of background replacement system and method for bullet time special efficacy, wherein system include that green curtain scratches module, are handled the optimum image being originally inputted for scratching nomography using green curtain, to obtain the first foreground image;Shade separation module, for detaching moving object and shade in first foreground image, to obtain the second foreground image;Image synthesis unit, for second foreground image to be merged with default background, cruel image is dazzled in formation, and for bullet time special effect making, the present invention is used for the background replacement system and method for bullet time special efficacy, figure is scratched by using green curtain, and the method being combined is detached with shade, more accurate foreground image is extracted, and the foreground of separation is synthesized in background that is more rich, more extremely dazzling, is used for bullet time special effect making, improve the bullet time dazzles cruel special efficacy, enhances user experience.
Description
Technical field
The invention belongs to camera work fields, and in particular to a kind of background replacement system and side for bullet time special efficacy
Method.
Background technology
" bullet time (Bullet time) " is referred to as " time cutting " or " time freezes ", is a kind of use in electricity
In shadow, television advertising or computer game, with computer assisted camera work simulate speed change special efficacy, such as the slow motion of reinforcing,
Time is static and other effects.The film that the bullet time produces in Hollywood film company of Warner Brothers《The Matrix》In, it is used for table
Existing leading man hides the scene of bullet and well known to the public.
The bullet time has camera array, one camera shooting, scene stillness, CG animations, multimachine position to repeat five kinds of shootings of shooting
Pattern.The bullet time is realized with a series of stationary cameras around object.These camera arrays usually by simultaneously or
Person's sequence trigger switch shutter.Combine each photograph frame that each camera is shot the vision rotation that can be formed by stationary object
Turn effect or super slow motion effect.Its feature is that not only extreme variation is (static or slow to being enough to show in time
Under normal circumstances not can it is observed that the phenomenon that), and spatially extreme variation.
To form the visual effect more extremely dazzled, the back of the body of bullet time special efficacy can be enriched by image processing techniques means
Scape brings the visual experience of more picture sense.A kind of background alternative of present invention offer and method scratch figure and the moon using green curtain
Shadow isolation technics, by video image foreground and background information detach, and by the foreground of separation be synthesized to it is more rich, more extremely dazzle
Background in, form magical visual effect.
Existing green curtain scratches nomography, and the flatness and light environment requirement to green curtain background are relatively high, such as light is not
Uniformly it be easy to cause that foreground edge is unsmooth, has larger shade etc., green curtain background unevenness to easy to produce noise etc. in foreground.
Accordingly, it is desirable to provide a kind of more effective background replacement method.
Invention content
In the prior art, green curtain scratches nomography, and the flatness and light environment requirement to green curtain background are relatively high, such as light
Line is uneven to be easy to cause that foreground edge is unsmooth, has larger shade etc., green curtain background unevenness to easy to produce noise in foreground
Deng in order to solve this problem, the present invention provides a kind of background replacement system for bullet time special efficacy, and concrete scheme is such as
Under:
A kind of background replacement system for bullet time special efficacy is applied in bullet time manufacturing system, wherein this is
System includes:
Green curtain scratches module, is handled the optimum image being originally inputted for scratching nomography using green curtain, to obtain
First foreground image;
Shade separation module, for detaching moving object and shade in first foreground image, before obtaining second
Scape image;
Image synthesis unit, for merging second foreground image with default background, cruel image is dazzled in formation, for
Bullet time special effect making.
Wherein, in above system, the green curtain is scratched in module, and figure is originally inputted for the green curtain FIG pull handle
As opening optimum images to choose the N of module selection automatically for the optimum image in bullet time manufacturing system, and the N optimal
Image corresponds to the optimum image of the bullet time N number of camera of manufacturing system respectively;
Algorithm used by the green curtain FIG pull handle is trimap methods or deep learning method.
Wherein, in above system, the green curtain is scratched and is additionally provided with denoising mould between module and the shade separation module
Block;
The denoising module is used to carry out out operation processing to the first foreground image, or carries out closed operation processing, Huo Zhejin
Row opens the combined treatment of operation and closed operation;
The operation of opening to the first foreground image is first to corrode to expand afterwards, to remove the discrete noise in background;
The closed operation to the first foreground image is first to expand to corrode again, with the empty noise in removal foreground.
Wherein, in above system, moving object and the moon in the first foreground image are detached in the shade separation module
Shadow need to select effective moving object shade separation algorithm according to different application scenarios.
Wherein, in above system, described image synthesis module uses progressive integration technology, according to mask images by
Two foreground images are merged with default background image, and are smoothed, so that mistake at cruel image boundary is dazzled in synthesis
Cross nature;
Synthesize obtain dazzle cruel image, as the input picture of the image processing module in bullet time manufacturing system,
Image processing module carries out the stabilization processing of brightness uniformity adjustment, aberration consistency adjustment and image, and then generates bullet
Time special efficacy.
In the background replacement system for bullet time special efficacy of the present invention, is scratched using green curtain and scheme to detach with shade to be combined
Method, extract more accurate foreground image, and the foreground of separation is synthesized in background that is more rich, more extremely dazzling, be used for
Bullet time special effect making, improve the bullet time dazzles cruel special efficacy, enhances user experience.
According to another aspect of the present invention, the present invention also provides a kind of background replacement sides for bullet time special efficacy
Method specifically comprises the following steps:
Step S1, it is based on optimum image and carries out green curtain FIG pull handle, to obtain the first foreground image;
Step S2, moving object and the shade in first foreground image are detached, to obtain the second foreground image;
Step S3, second foreground image is merged with default background, cruel image is dazzled in formation, for bullet time spy
Effect makes.
Wherein, in the above-mentioned methods, green curtain FIG pull handle is carried out based on optimum image in the step S1, to obtain first
Foreground image specifically includes:
Original input picture for green curtain FIG pull handle is automatic for the optimum image in bullet time manufacturing system
The N optimum images that module is chosen are chosen, and the N optimum images correspond to the bullet time N number of camera of manufacturing system most respectively
Excellent image;
Algorithm used by green curtain FIG pull handle is trimap methods or deep learning method.
Wherein, in the above-mentioned methods, following steps are additionally provided between the step S1 and step S2:
Operation processing is carried out out to the first foreground image, or carries out closed operation processing, or carries out out operation and closed operation
Combined treatment;
The operation of opening to the first foreground image is first to corrode to expand afterwards, to remove the discrete noise in background;
The closed operation to the first foreground image is first to expand to corrode again, with the empty noise in removal foreground.
Wherein, in the above-mentioned methods, moving object and the shade in first foreground image are detached in the step S2,
It is specifically included with obtaining the second foreground image:
Detaching moving object and shade in the first foreground image need to select effectively to transport according to different application scenarios
Animal body shade separation algorithm.
Wherein, in the above-mentioned methods, second foreground image is merged with default background in the step S3, formation is dazzled
Cruel image specifically includes for bullet time special effect making:
Using progressive integration technology, the second foreground image is merged with default background image according to mask images, and
It is smoothed, so that transition nature at cruel image boundary is dazzled in synthesis;
Synthesize obtain dazzle cruel image, as the input picture of the image processing module in bullet time manufacturing system,
Image processing module carries out the stabilization processing of brightness uniformity adjustment, aberration consistency adjustment and image, and then generates bullet
Time special efficacy.
In the background replacement method for bullet time special efficacy of the present invention, is scratched using green curtain and scheme to detach with shade to be combined
Method, extract more accurate foreground image, and the foreground of separation is synthesized in background that is more rich, more extremely dazzling, be used for
Bullet time special effect making, improve the bullet time dazzles cruel special efficacy, enhances user experience.
Description of the drawings
Fig. 1 is the background replacement system structural schematic diagram for bullet time special efficacy that an embodiment of the present invention provides;
Fig. 2 is the background replacement method flow chart for bullet time special efficacy that second embodiment of the invention provides.
Specific implementation mode
In order to make the objectives, technical solutions and advantages of the present invention clearer, With reference to embodiment and join
According to attached drawing, the present invention is described in more detail.It should be understood that these descriptions are merely illustrative, and it is not intended to limit this hair
Bright range.In addition, in the following description, descriptions of well-known structures and technologies are omitted, to avoid this is unnecessarily obscured
The concept of invention.
The bullet time has camera array, one camera shooting, scene stillness, CG animations, multimachine position to repeat five kinds of shootings of shooting
Pattern.The bullet time is realized with a series of stationary cameras around object.These camera arrays usually by simultaneously or
Person's sequence trigger switch shutter.Combine each photograph frame that each camera is shot the vision rotation that can be formed by stationary object
Turn effect or super slow motion effect.Its feature is that not only extreme variation is (static or slow to being enough to show in time
Under normal circumstances not can it is observed that the phenomenon that), and spatially extreme variation.
To form the visual effect more extremely dazzled, the back of the body of bullet time special efficacy can be enriched by image processing techniques means
Scape brings the visual experience of more picture sense.A kind of background alternative of present invention offer and method scratch figure and the moon using green curtain
Shadow isolation technics, by video image foreground and background information detach, and by the foreground of separation be synthesized to it is more rich, more extremely dazzle
Background in, form magical visual effect.
Existing green curtain scratches nomography, and the flatness and light environment requirement to green curtain background are relatively high, such as light is not
Uniformly it be easy to cause that foreground edge is unsmooth, has larger shade etc., green curtain background unevenness to easy to produce noise etc. in foreground.
In this case, it is desirable to provide a kind of more effective background replacement method, to improve the vision of bullet time special efficacy
Effect, the background replacement system and method for bullet time special efficacy provided by this programme use green curtain and scratch figure and the moon
Shadow detaches the method that is combined, can extract out more accurate foreground image, and by the foreground of separation be synthesized to it is more rich, more extremely dazzle
Background in, for bullet time special effect making, the bullet time can be improved dazzles cruel special efficacy, enhances user experience.
Provided by the present invention for the background replacement system of bullet time special efficacy, it is applied in bullet time manufacturing system,
As shown in Figure 1, specifically including following module:
Green curtain scratches module 11, is handled the optimum image being originally inputted for scratching nomography using green curtain, with
To the first foreground image;
Shade separation module 12, for detaching moving object and shade in first foreground image, to obtain second
Foreground image;
Image synthesis unit 13 is formed and dazzles cruel image for merging second foreground image with default background, with
In bullet time special effect making.
In specific implementation, the green curtain is scratched in module 11, and the original input picture for the green curtain FIG pull handle is
Choose N optimum images of module selection, and the N optimum images automatically for the optimum image in bullet time manufacturing system
The optimum image of the bullet time N number of camera of manufacturing system is corresponded to respectively;
After getting optimum image, nomography is scratched using green curtain and extracts initial foreground image from original image, for difference
The foreground image obtained after different operation subsequently is carried out to image, initial foreground image is defined as the first foreground image;
Algorithm used by the green curtain FIG pull handle is trimap methods or deep learning method.
In specific implementation, the green curtain is scratched and is additionally provided with denoising module between module and the shade separation module, due to
The reasons such as light is uneven, green curtain unevenness can so that curtain color light and shade is uneven, and then green curtain is caused to scratch what nomography obtained
First foreground image contains discrete noise, it is also possible to the shade of large area is generated, therefore, in shade separation module separation described the
Before moving object and shade in one foreground image, denoising module can be further reduced the discrete noise in foreground image;
The denoising module is used to carry out out operation processing to the first foreground image, or carries out closed operation processing, Huo Zhejin
Row opens the combined treatment of operation and closed operation;
The operation of opening to the first foreground image is first to corrode to expand afterwards, to remove the discrete noise in background;
The closed operation to the first foreground image is first to expand to corrode again, with the empty noise in removal foreground.
In specific implementation, the moving object and shade that are detached in the shade separation module 12 in first foreground image need root
Effective moving object shade separation algorithm is selected according to different application scenarios, during bullet time special effect making, when
When illumination or uneven light-illuminating, the region that moving object is blocked can form shade in the picture, therefore, the first foreground picture
It may include moving object region and shadow region as in need to be selected according to different application scenarios in practical applications
Effective moving object shade separation algorithm.
Such as:When the color attribute of moving object has apparent difference with movement shade, brightness, chromaticity can be used
Preferably detach shade;When texture information enriches, textural characteristics can be based on and distinguish moving object and shade;Field can also be used
The prior informations such as scape, light source direction and moving target shape establish shadow model, and object pixel and the moon are distinguished according to shadow model
Image element, the method are suitable for simple indoor and outdoor scene, are also not limited to the above several method certainly, also can be used other
Method carries out moving object and its shade separation.
In specific implementation, described image synthesis module uses progressive integration technology, according to mask images by the second foreground
Image is merged with default background image, and is smoothed, so that transition nature at cruel image boundary is dazzled in synthesis;
Synthesize obtain dazzle cruel image, as the input picture of the image processing module in bullet time manufacturing system,
Image processing module carries out the stabilization processing of brightness uniformity adjustment, aberration consistency adjustment and image, and then generates bullet
Time special efficacy.
In the background replacement system for bullet time special efficacy of the present invention, is scratched using green curtain and scheme to detach with shade to be combined
Method, extract more accurate foreground image, and the foreground of separation is synthesized in background that is more rich, more extremely dazzling, be used for
Bullet time special effect making, improve the bullet time dazzles cruel special efficacy, enhances user experience.
According to another aspect of the present invention, as shown in Fig. 2, the present invention also provides a kind of for bullet time special efficacy
Background replacement method, specifically comprises the following steps:
Step S1, it is based on optimum image and carries out green curtain FIG pull handle, to obtain the first foreground image;
Step S2, moving object and the shade in first foreground image are detached, to obtain the second foreground image;
Step S3, second foreground image is merged with default background, cruel image is dazzled in formation, for bullet time spy
Effect makes.
In specific implementation, green curtain FIG pull handle is carried out based on optimum image in the step S1, to obtain the first foreground picture
As specifically including:
Original input picture for green curtain FIG pull handle is automatic for the optimum image in bullet time manufacturing system
The N optimum images that module is chosen are chosen, and the N optimum images correspond to the bullet time N number of camera of manufacturing system most respectively
Excellent image;
After getting optimum image, nomography is scratched using green curtain and extracts initial foreground image from original image, for difference
The foreground image obtained after different operation subsequently is carried out to image, initial foreground image is defined as the first foreground image;
Algorithm used by green curtain FIG pull handle is trimap methods or deep learning method.
In specific implementation, since light is uneven, can so that curtain color light and shade is uneven due to green curtain unevenness etc., in turn
Cause green curtain to scratch the first foreground image that nomography obtains and contains discrete noise, it is also possible to the shade of large area is generated, therefore,
Before executing step S2, in order to be further reduced the discrete noise in foreground image, the first foreground image need to be carried out at denoising
Reason, following steps are additionally provided between the step S1 and step S2:
Operation processing is carried out out to the first foreground image, or carries out closed operation processing, or carries out out operation and closed operation
Combined treatment;
The operation of opening to the first foreground image is first to corrode to expand afterwards, to remove the discrete noise in background;
The closed operation to the first foreground image is first to expand to corrode again, with the empty noise in removal foreground.
In specific implementation, the moving object in first foreground image and shade are detached in the step S2, to obtain
Second foreground image specifically includes:
During bullet time special effect making, when illumination or uneven light-illuminating, area that moving object is blocked
Domain can form shade in the picture, may include moving object region and shadow region in the first foreground image, in reality therefore
In the application of border, the moving object and shade that detach in the first foreground image need to select effectively to transport according to different application scenarios
Animal body shade separation algorithm.
Such as:When the color attribute of moving object has apparent difference with movement shade, brightness, chromaticity can be used
Preferably detach shade;When texture information enriches, textural characteristics can be based on and distinguish moving object and shade;Field can also be used
The prior informations such as scape, light source direction and moving target shape establish shadow model, and object pixel and the moon are distinguished according to shadow model
Image element, the method are suitable for simple indoor and outdoor scene, are also not limited to the above several method certainly, also can be used other
Method carries out moving object and its shade separation.
In specific implementation, second foreground image to be merged with default background in the step S3, cruel image is dazzled in formation,
It is specifically included for bullet time special effect making:
Using progressive integration technology, the second foreground image is merged with default background image according to mask images, and
It is smoothed, so that transition nature at cruel image boundary is dazzled in synthesis;
Synthesize obtain dazzle cruel image, as the input picture of the image processing module in bullet time manufacturing system,
Image processing module carries out the stabilization processing of brightness uniformity adjustment, aberration consistency adjustment and image, and then generates bullet
Time special efficacy.
In the background replacement method for bullet time special efficacy of the present invention, is scratched using green curtain and scheme to detach with shade to be combined
Method, extract more accurate foreground image, and the foreground of separation is synthesized in background that is more rich, more extremely dazzling, be used for
Bullet time special effect making, improve the bullet time dazzles cruel special efficacy, enhances user experience.
It should be understood that the above-mentioned specific implementation mode of the present invention is used only for exemplary illustration or explains the present invention's
Principle, but not to limit the present invention.Therefore, that is done without departing from the spirit and scope of the present invention is any
Modification, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.In addition, appended claims purport of the present invention
Covering the whole variations fallen into attached claim scope and boundary or this range and the equivalent form on boundary and is repairing
Change example.
Claims (10)
1. a kind of background replacement system for bullet time special efficacy is applied in bullet time manufacturing system, which is characterized in that
Including:
Green curtain scratches module, is handled the optimum image being originally inputted for scratching nomography using green curtain, to obtain first
Foreground image;
Shade separation module, for detaching moving object and shade in first foreground image, to obtain the second foreground picture
Picture;
Image synthesis unit, for merging second foreground image with default background, cruel image is dazzled in formation, for bullet
Time special effect making.
2. system according to claim 1, which is characterized in that the green curtain is scratched in module, and figure is scratched for the green curtain
The original input picture of processing be chosen automatically for the optimum image in bullet time manufacturing system module selection N it is optimal
Image, and the N optimum images correspond to the optimum image of the bullet time N number of camera of manufacturing system respectively;
Algorithm used by the green curtain FIG pull handle is trimap methods or deep learning method.
3. system according to claim 1, which is characterized in that the green curtain scratch module and the shade separation module it
Between be additionally provided with denoising module;
The denoising module is used to carry out out operation processing to the first foreground image, or carries out closed operation processing, or is opened
The combined treatment of operation and closed operation;
The operation of opening to the first foreground image is first to corrode to expand afterwards, to remove the discrete noise in background;
The closed operation to the first foreground image is first to expand to corrode again, with the empty noise in removal foreground.
4. system according to claim 1, which is characterized in that detached in the first foreground image in the shade separation module
Moving object and shade effective moving object shade separation algorithm need to be selected according to different application scenarios.
5. system according to claim 1, which is characterized in that described image synthesis module uses progressive integration technology,
The second foreground image is merged with default background image according to mask images, and is smoothed, so that synthesis
It is natural to dazzle transition at cruel image boundary;
What synthesis obtained dazzles cruel image, as the input picture of the image processing module in bullet time manufacturing system, image
Processing module carries out the stabilization processing of brightness uniformity adjustment, aberration consistency adjustment and image, and then generates the bullet time
Special efficacy.
6. a kind of background replacement method for bullet time special efficacy, which is characterized in that include the following steps:
Step S1, it is based on optimum image and carries out green curtain FIG pull handle, to obtain the first foreground image;
Step S2, moving object and the shade in first foreground image are detached, to obtain the second foreground image;
Step S3, second foreground image is merged with default background, cruel image is dazzled in formation, for bullet time special efficacy system
Make.
7. according to the method described in claim 6, it is characterized in that, carrying out green curtain based on optimum image in the step S1 scratches figure
Processing, is specifically included with obtaining the first foreground image:
Original input picture for green curtain FIG pull handle is to be chosen automatically for the optimum image in bullet time manufacturing system
The N optimum images that module is chosen, and the N optimum images correspond to the optimal figure of the bullet time N number of camera of manufacturing system respectively
Picture;
Algorithm used by green curtain FIG pull handle is trimap methods or deep learning method.
8. according to the method described in claim 6, it is characterized in that, being additionally provided with following step between the step S1 and step S2
Suddenly:
Operation processing is carried out out to the first foreground image, or carries out closed operation processing, or carries out out the group of operation and closed operation
Conjunction is handled;
The operation of opening to the first foreground image is first to corrode to expand afterwards, to remove the discrete noise in background;
The closed operation to the first foreground image is first to expand to corrode again, with the empty noise in removal foreground.
9. according to the method described in claim 6, it is characterized in that, being detached in the step S2 in first foreground image
Moving object and shade are specifically included with obtaining the second foreground image:
Effective moving object need to be selected according to different application scenarios by detaching moving object and shade in the first foreground image
Body shade separation algorithm.
10. according to the method described in claim 6, it is characterized in that, by second foreground image and in advance in the step S3
If background merges, cruel image is dazzled in formation, is specifically included for bullet time special effect making:
Using progressive integration technology, the second foreground image is merged with default background image according to mask images, and carries out
Smoothing processing, so that transition nature at cruel image boundary is dazzled in synthesis;
What synthesis obtained dazzles cruel image, as the input picture of the image processing module in bullet time manufacturing system, image
Processing module carries out the stabilization processing of brightness uniformity adjustment, aberration consistency adjustment and image, and then generates the bullet time
Special efficacy.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810372971.7A CN108683865A (en) | 2018-04-24 | 2018-04-24 | A kind of background replacement system and method for bullet time special efficacy |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810372971.7A CN108683865A (en) | 2018-04-24 | 2018-04-24 | A kind of background replacement system and method for bullet time special efficacy |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108683865A true CN108683865A (en) | 2018-10-19 |
Family
ID=63801318
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810372971.7A Pending CN108683865A (en) | 2018-04-24 | 2018-04-24 | A kind of background replacement system and method for bullet time special efficacy |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108683865A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111479036A (en) * | 2019-01-24 | 2020-07-31 | 上海赢赞数字科技有限公司 | Bullet time special effect shooting system and method based on camera |
CN112200756A (en) * | 2020-10-09 | 2021-01-08 | 电子科技大学 | Intelligent bullet special effect short video generation method |
CN112261245A (en) * | 2020-10-27 | 2021-01-22 | 苏州光魔方智能数字科技有限公司 | VR bullet time shooting interaction system |
CN112468728A (en) * | 2020-11-27 | 2021-03-09 | 努比亚技术有限公司 | Video synthesis method, video synthesis equipment and computer-readable storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104933728A (en) * | 2015-07-13 | 2015-09-23 | 天津理工大学 | Mixed motion target detection method |
CN105335985A (en) * | 2014-08-01 | 2016-02-17 | 深圳中集天达空港设备有限公司 | Real-time capture method and system of docking airplane on the basis of machine vision |
CN206313885U (en) * | 2016-12-27 | 2017-07-07 | 湖南子午天地科技文化发展有限公司 | A kind of monopod video camera array made for the bullet time |
US20170208238A1 (en) * | 2016-01-14 | 2017-07-20 | Xiaoyi Technology Co., Ltd. | System and method for bullet-time photography |
CN107886502A (en) * | 2017-10-24 | 2018-04-06 | 天津大学 | The shadow Detection and removal algorithm of color and gradient synthesis under a kind of complex environment |
-
2018
- 2018-04-24 CN CN201810372971.7A patent/CN108683865A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105335985A (en) * | 2014-08-01 | 2016-02-17 | 深圳中集天达空港设备有限公司 | Real-time capture method and system of docking airplane on the basis of machine vision |
CN104933728A (en) * | 2015-07-13 | 2015-09-23 | 天津理工大学 | Mixed motion target detection method |
US20170208238A1 (en) * | 2016-01-14 | 2017-07-20 | Xiaoyi Technology Co., Ltd. | System and method for bullet-time photography |
CN206313885U (en) * | 2016-12-27 | 2017-07-07 | 湖南子午天地科技文化发展有限公司 | A kind of monopod video camera array made for the bullet time |
CN107886502A (en) * | 2017-10-24 | 2018-04-06 | 天津大学 | The shadow Detection and removal algorithm of color and gradient synthesis under a kind of complex environment |
Non-Patent Citations (1)
Title |
---|
杨卫英等: "《第十三届全国图象图形学学术会议论文集》", 6 November 2006 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111479036A (en) * | 2019-01-24 | 2020-07-31 | 上海赢赞数字科技有限公司 | Bullet time special effect shooting system and method based on camera |
CN112200756A (en) * | 2020-10-09 | 2021-01-08 | 电子科技大学 | Intelligent bullet special effect short video generation method |
CN112261245A (en) * | 2020-10-27 | 2021-01-22 | 苏州光魔方智能数字科技有限公司 | VR bullet time shooting interaction system |
CN112468728A (en) * | 2020-11-27 | 2021-03-09 | 努比亚技术有限公司 | Video synthesis method, video synthesis equipment and computer-readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108683865A (en) | A kind of background replacement system and method for bullet time special efficacy | |
US10477005B2 (en) | Portable electronic devices with integrated image/video compositing | |
CN107493488B (en) | Method for intelligently implanting video content based on Faster R-CNN model | |
CN109191558B (en) | Image polishing method and device | |
CN108257084B (en) | Lightweight face automatic makeup method based on mobile terminal | |
US8761497B2 (en) | Removal of shadows from images in a video signal | |
Baba et al. | Shadow removal from a real image based on shadow density | |
US20110074778A1 (en) | Method and system for creating depth and volume in a 2-d planar image | |
CN106169182B (en) | A method of synthesizing several different exposure images | |
CN105931208B (en) | Enhancement algorithm for low-illumination image based on physical model | |
US11425283B1 (en) | Blending real and virtual focus in a virtual display environment | |
US20070086652A1 (en) | Apparatus, medium, and method with facial-image-compensation | |
CN103955918A (en) | Full-automatic fine image matting device and method | |
Aliaga et al. | A virtual restoration stage for real-world objects | |
WO2020019164A1 (en) | Video processing method and device, and computer-readable storage medium | |
CN112384928A (en) | Method and apparatus for performing object illumination manipulation on an image | |
Lv et al. | Low-light image enhancement via deep Retinex decomposition and bilateral learning | |
Liba et al. | Sky optimization: Semantically aware image processing of skies in low-light photography | |
CN109859303A (en) | Rendering method, device, terminal device and the readable storage medium storing program for executing of image | |
CN114902277A (en) | System and method for processing shadows on portrait image frames | |
CN109949400B (en) | Shadow estimation and reconstruction method suitable for AR virtual soft-loading synthesis | |
CN114140360A (en) | Local low-visibility image enhancement method | |
US8063991B2 (en) | Using a region restricted cleanup signal to bridge a signal level mismatch between a blue screen and an adjoining garbage matte | |
US11798214B2 (en) | Enhanced hybrid animation | |
CN112785504B (en) | Day and night image fusion method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181019 |
|
RJ01 | Rejection of invention patent application after publication |