CN106780354A - Multiple image clearness processing method and device - Google Patents
Multiple image clearness processing method and device Download PDFInfo
- Publication number
- CN106780354A CN106780354A CN201611000429.6A CN201611000429A CN106780354A CN 106780354 A CN106780354 A CN 106780354A CN 201611000429 A CN201611000429 A CN 201611000429A CN 106780354 A CN106780354 A CN 106780354A
- Authority
- CN
- China
- Prior art keywords
- image
- definition picture
- target signature
- location
- change
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 13
- 230000008859 change Effects 0.000 claims abstract description 50
- 230000004927 fusion Effects 0.000 claims abstract description 25
- 239000000654 additive Substances 0.000 claims abstract description 21
- 230000000996 additive effect Effects 0.000 claims abstract description 21
- 230000003321 amplification Effects 0.000 claims abstract description 16
- 238000003199 nucleic acid amplification method Methods 0.000 claims abstract description 16
- 238000006073 displacement reaction Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 10
- 238000003707 image sharpening Methods 0.000 claims description 9
- 230000005012 migration Effects 0.000 claims description 8
- 238000013508 migration Methods 0.000 claims description 8
- 238000000034 method Methods 0.000 abstract description 10
- 238000011840 criminal investigation Methods 0.000 abstract description 5
- 230000008569 process Effects 0.000 abstract description 5
- 230000009286 beneficial effect Effects 0.000 abstract description 4
- 230000000694 effects Effects 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000002156 mixing Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
Classifications
-
- G06T5/73—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4053—Super resolution, i.e. output image resolution higher than sensor resolution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Abstract
Present invention is disclosed a kind of multiple image clearness processing method and device, method is comprised the following steps:Pending image is carried out into pixel replicability amplification, the high-definition picture after being amplified;The target signature in high-definition picture is chosen, change in location of the target signature in high-definition picture is determined, and target signature position is reduced according to change in location, target signature is in same position in high-definition picture;By all high-definition picture additive fusions.The beneficial effects of the invention are as follows:Original image is amplified by replicability, increase the pixel unit of basic pixel, reduce the occupancy size of each pixel, calculate the mobile data of realistic objective feature, obtain obtaining target signature clearly image by measuring and calculating target signature mobile distance actual less than 1 location of pixels, the target signature border for being become apparent from, last additive fusion in image, process is easy and effective, obtains can be used for enough clearly images of criminal investigation scene.
Description
Technical field
The present invention relates to multiple image process field, especially relate to a kind of multiple image clearness processing method and
Device.
Background technology
At present, in video surveillance applications, usually because the object distance camera of appearance is distant in video and monitors
The problem of equipment image quality, the pixel total amount that single-frame images is imaged in video in itself is few (being commonly called as resolution ratio low), it is impossible to logical
The effective information for recognizing the need for of image crossed video and wherein include.And, it is necessary to often call in normal criminal investigation activity
Monitor video or image are analyzed, and obtain the information needed in monitor video or image, such as vehicle license, specific word letter
The appearance information of breath or particular person.
In existing Sharp processing of image method, have and directly increased by amplifying the pixel quantity of original picture at double
The resolution sizes of image, the purpose of original image pixel boundary is amplified so as to reach, but cannot cause by this method
Image becomes apparent from.
The content of the invention
The main object of the present invention to provide a kind of multiple image clearness processing method and device, can effectively improve into
As the pixel total amount of video image, and sharpening treatment is done to video image.
The present invention proposes a kind of multiple image clearness processing method, comprises the following steps:
Pending image is carried out into pixel replicability amplification, the high-definition picture after being amplified;
The target signature in high-definition picture is chosen, change in location of the target signature in high-definition picture is determined,
And target signature position is reduced according to change in location, target signature is in same position in high-definition picture;
By all high-definition picture additive fusions.
Further, it is described that pending image is carried out into pixel replicability amplification, the high-definition picture after being amplified
Before step, including,
Video file is resolved into multiple images according to the frame number of itself, and is arranged in order according to image frame sequential.
Further, the target signature chosen in high-definition picture, determines target signature in high-definition picture
In change in location, and target signature position is reduced according to change in location, be in target signature identical in high-definition picture
Position step, including,
High-definition picture after amplification is replicated, corresponding high-resolution sample image is obtained, to high-resolution
Image pattern carries out Gaussian Blur computing or goes Gaussian Blur computing;
Latter two field picture is moved with reference to previous frame image, when the target signature center on image or edge contour are overlapped,
Record each change in location data of high-resolution sample image, and by change in location data migration to former high resolution graphics
Picture.
Further, it is described by all edge image fusion superposition steps, including,
Position mobile data in high-definition picture, by the superposition of all image co-registrations.
The invention allows for a kind of multiple image sharpening processing unit, including:
Amplifying unit, for pending image to be carried out into pixel replicability amplification, the high-definition picture after being amplified;
Position recovering unit, for choosing the target signature in high-definition picture, determines target signature in high-resolution
Change in location in image, and target signature position is reduced according to change in location, target signature is in high-definition picture
Same position;
Additive fusion unit, for by all high-definition picture additive fusions.
Further, also include, pretreatment unit, for video file to be resolved into multiple figures according to the frame number of itself
Picture, and be arranged in order according to image frame sequential.
Further, the position recovering unit, including,
Edge treated module, for the high-definition picture after amplification to be replicated, obtains corresponding high-resolution sample
This image, carries out Gaussian Blur computing or goes Gaussian Blur computing to high-definition picture sample;
Displacement acquisition module, for moving latter two field picture with reference to previous frame image, when the target signature center on image
Or during edge contour overlap, each change in location data of high-resolution sample image are recorded, and change in location data are moved
Plant original high resolution image.
Further, the additive fusion unit, including additive fusion module, for the position in high-definition picture
Mobile data is put, by the superposition of all image co-registrations.
The beneficial effects of the invention are as follows:Original image is amplified by replicability, increases the pixel unit of basic pixel, reduce every
The occupancy size of individual pixel, calculates the mobile data of realistic objective feature, obtains being less than 1 picture by measuring and calculating target signature in image
The actual mobile distance in plain position, the target signature border for being become apparent from, it is clear that last additive fusion obtains target signature
Image, process is easy and effective, obtains can be used for the clearly image enough of criminal investigation scene.
Brief description of the drawings
Fig. 1 is a kind of FB(flow block) of multiple image clearness processing method of one embodiment of the invention;
Fig. 2 is a kind of particular flow sheet of the step of multiple image clearness processing method one of one embodiment of the invention;
Fig. 3 is a kind of structured flowchart of multiple image sharpening processing unit of one embodiment of the invention;
Fig. 4 is a kind of structural frames of the position recovering unit of multiple image sharpening processing unit of one embodiment of the invention
Figure;
Fig. 5 is a kind of structural frames of the additive fusion unit of multiple image sharpening processing unit of one embodiment of the invention
Figure.
The realization of the object of the invention, functional characteristics and advantage will be described further referring to the drawings in conjunction with the embodiments.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singulative " " used herein, " one
It is individual ", " described " and " being somebody's turn to do " may also comprise plural form.It is to be further understood that what is used in specification of the invention arranges
Diction " including " refer to the presence of the feature, integer, step, operation, element and/or component, but it is not excluded that in the presence of or addition
One or more other features, integer, step, operation, element, component and/or their group.Wording used herein " and/
Or " include one or more associated wholes or any cell of listing item and all combine.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, all terms used herein (including technology art
Language and scientific terminology), with art of the present invention in those of ordinary skill general understanding identical meaning.Should also
Understand, those terms defined in such as general dictionary, it should be understood that with the context with prior art
The consistent meaning of meaning, and unless by specific definitions as here, will not otherwise use idealization or excessively formal implication
To explain.
Reference picture 1-2, proposes a kind of multiple image clearness processing method of one embodiment of the invention, comprises the following steps:
S1, video file is resolved into multiple images according to the frame number of itself, and be arranged in order according to image frame sequential.
S2, pending image is carried out pixel replicability amplification, the high resolution graphics after being amplified.
S3, the target signature chosen in high-definition picture, determine that position of the target signature in high-definition picture becomes
Change, and target signature position is reduced according to change in location, target signature is in same position in high-definition picture.
S4, by all high-definition picture additive fusions.
As described in above-mentioned step S1, wherein, the video file frame number of each second is certain, that is, a period of time length
Video file in the static images quantity that includes be fixed, and generally many frames, per two field picture between priority it is suitable
Sequence is fixed, and video file can be decomposed into several by us the image of sequencing, and is being regarded according to each two field picture
The time order and function occurred in frequency file carrys out number consecutively sequence, for the relation between image before and after understanding, convenient follow-up ratio
Relatively and obtain the change in location of target signature in the image of front and rear frame.
Above-mentioned video file, includes us and wants the target signature of sharpening, and it can further be recorded for monitoring
As file, during practical application, the time occurred in video file according to target signature and the time for disappearing intercept monitoring video
File, to carry out follow-up operation.Actual, target signature can be license board information, the face information of appearance in video file
Or other need the accurate visual information for understanding.
As described in above-mentioned step S2, when object is subjected to displacement in video or image, object pixel imaging can be with thing
The different imaging of the mobile generation of body, is reduced to single pixel (the black thing of white background), and original state is that a location of pixels is 100% black,
B location of pixels 100% is white, by black pixel from the b location of pixels that a location of pixels is moved fully to adjacent, now b location of pixels
For 100% is black, a location of pixels 100% is white, and this is the complete migration of pixel;Percent 70% stay in a after pixel is moved
Location of pixels, and 30% is moved to b location of pixels, according to Law of Barrel, a location of pixels is 70% black, and b location of pixels is
30% is black, that is, original pixel cannot be independently present between a location of pixels and b location of pixels, accordingly even when to image
Fusion is overlapped, cannot also obtain containing clearly target signature image.To carrying out pixel replicability amplification in step S2, it is
Refer to resolve into original pixel and take smaller pixel unit, such as, by original a pixels, be divided into 4*4 a1Pixel, decomposes
A afterwards1It is 1st/16th of original a pixels that pixel takes size, and so when pixel is subjected to displacement, we can be with
By a small margin displacement of the pixel less than 1 pixel unit is obtained, it is corresponding to obtain more accurate target signature marginal information.
Such as above-mentioned step S3, comprise the following steps,
S31, the high-definition picture after amplification is replicated, corresponding high-resolution sample image is obtained, to high score
Resolution image pattern carries out Gaussian Blur computing or goes Gaussian Blur computing.
S32, reference previous frame image move latter two field picture, when the target signature center on image or edge contour are overlapped
When, record each change in location data of high-resolution sample image, and by change in location data migration to former high-resolution
Image.
As above described in step S31, when smear out effect is carried out to high-definition picture, adjoining pixel can occur pixel friendship
Melt, so that overall colour gamut produces border virtualization phenomenon, now the change in location of image entirety colour gamut is high-visible, and by position
Delta data feeds back to original high-definition picture.
In an alternative embodiment of the invention, it is possible to use deblurring algorithm, deblurring change is being carried out to high-definition picture
During change, while adjoining pixel can occur pixel blending, secondary edge is calculated, now image integral edge is high-visible,
Change in location is also shown, and estimates displacement from according to modified-image, and original high-resolution is given by change in location data feedback
Rate image.
As above described in step S32, latter two field picture is moved with reference to previous frame image, can observe by the naked eye or computer from
Dynamic computing, when the center of target signature or edge contour are overlapped, the change in location data between record hypograph, and by position
Delta data is transplanted to original high resolution image.
Wherein, such as observe by the naked eye to judge change in location data, then need to record shifting of the image in x, y coordinate system
Dynamic distance, after completing superposition, by change in location data migration to original high resolution image.
As above described in step S4, the change in location number of target signature in front and rear two field pictures is can obtain by above-mentioned steps
According to, the image of superposition is available for by change in location data, the position of target signature is consistent in all images, most
All image co-registrations are superimposed afterwards, obtain clearly target signature image.
The beneficial effects of the invention are as follows:Original image is amplified by replicability, increases the pixel unit of basic pixel, reduce every
The occupancy size of individual pixel, calculates the mobile data of realistic objective feature, obtains being less than 1 picture by measuring and calculating target signature in image
The actual mobile distance in plain position, the target signature border for being become apparent from, it is clear that last additive fusion obtains target signature
Image, process is easy and effective, obtains can be used for the clearly image enough of criminal investigation scene.
Reference picture 3-5, the invention allows for a kind of multiple image sharpening processing unit, including:
Pretreatment unit 1, for video file to be resolved into multiple images according to the frame number of itself, and according to picture frame
Order is arranged in order.
Amplifying unit 2, for pending image to be carried out into pixel replicability amplification, the high resolution graphics after being amplified
Picture;
Position recovering unit 3, for choosing the target signature in high-definition picture, determines target signature in high-resolution
Change in location in image, and target signature position is reduced according to change in location, target signature is in high-definition picture
Same position;
Additive fusion unit 4, for by all high-definition picture additive fusions.
For pretreatment unit 1, wherein, the video file frame number of each second is certain, that is, a period of time length
Video file in the static images quantity that includes be fixed, and generally many frames, per two field picture between priority it is suitable
Sequence is fixed, and video file can be decomposed into several by us the image of sequencing, and is being regarded according to each two field picture
The time order and function occurred in frequency file carrys out number consecutively sequence, for the relation between image before and after understanding, convenient follow-up ratio
Relatively and obtain the change in location of target signature in the image of front and rear frame.
Above-mentioned video file, includes us and wants the target signature of sharpening, and it can further be recorded for monitoring
As file, during practical application, the time occurred in video file according to target signature and the time for disappearing intercept monitoring video
File, to carry out follow-up operation.Actual, target signature can be license board information, the face information of appearance in video file
Or other need the accurate visual information for understanding.
When amplifying unit 2 works, when object is subjected to displacement in video or image, object pixel imaging can be with object
The different imaging of mobile generation, be reduced to single pixel (the black thing of white background), original state is that a location of pixels is 100% black, b
Location of pixels 100% is white, by black pixel from the b location of pixels that a location of pixels is moved fully to adjacent, now b location of pixels
For 100% is black, a location of pixels 100% is white, and this is the complete migration of pixel;Percent 70% stay in a after pixel is moved
Location of pixels, and 30% is moved to b location of pixels, according to Law of Barrel, a location of pixels is 70% black, and b location of pixels is
30% is black, that is, original pixel cannot be independently present between a location of pixels and b location of pixels, accordingly even when to image
Fusion is overlapped, cannot also obtain containing clearly target signature image.To carrying out pixel replicability amplification in step S2, it is
Refer to resolve into original pixel and take smaller pixel unit, such as, by original a pixels, be divided into 4*4 a1Pixel, decomposes
A afterwards1It is 1st/16th of original a pixels that pixel takes size, and so when pixel is subjected to displacement, we can be with
By a small margin displacement of the pixel less than 1 pixel unit is obtained, it is corresponding to obtain more accurate target signature marginal information.
As shown in figure 4, position recovering unit 3, including, edge treated module 301 and displacement acquisition module 302.Edge
Reason module 301, for the high-definition picture after amplification to be replicated, obtains corresponding high-resolution sample image, to height
Image in different resolution sample carries out Gaussian Blur computing or goes Gaussian Blur computing.
Displacement acquisition module 302, for moving latter two field picture with reference to previous frame image, when in the target signature on image
When the heart or edge contour are overlapped, each change in location data of high-resolution sample image are recorded, and by change in location data
It is transplanted to original high resolution image.
Edge treated module 301, for carrying out smear out effect to high-definition picture, carries out adjoining picture during smear out effect
Element can occur pixel blending, so that overall colour gamut produces border virtualization phenomenon, now the change in location of image entirety colour gamut is clear
It is clear visible, and give original high-definition picture by change in location data feedback.
In an alternative embodiment of the invention, edge treated module 301 is by using deblurring algorithm, to high resolution graphics
When changing as carrying out deblurring, while adjoining pixel can occur pixel blending, secondary edge is calculated, now image entirety
Edge clear is visible, and change in location also shows, and estimates displacement from according to modified-image, and change in location data feedback is given
Original high-definition picture.
Wherein, such as observe by the naked eye to judge change in location data, then need to record shifting of the image in x, y coordinate system
Dynamic distance, after completing superposition, by change in location data migration to original high resolution image.
Additive fusion unit 4, including additive fusion module 401, number is moved for the position in high-definition picture
According to by the superposition of all image co-registrations.The change in location data of target signature in front and rear two field pictures are obtained, by change in location number
According to the image for being available for superposition, the position of target signature is consistent in all images, finally by all image co-registrations
Superposition, obtains clearly target signature image.
The beneficial effects of the invention are as follows:Original image is amplified by replicability, increases the pixel unit of basic pixel, reduce every
The occupancy size of individual pixel, calculates the mobile data of realistic objective feature, obtains being less than 1 picture by measuring and calculating target signature in image
The actual mobile distance in plain position, the target signature border for being become apparent from, it is clear that last additive fusion obtains target signature
Image, process is easy and effective, obtains can be used for the clearly image enough of criminal investigation scene.
The preferred embodiments of the present invention are the foregoing is only, the scope of the claims of the invention, every utilization is not thereby limited
Equivalent structure or equivalent flow conversion that description of the invention and accompanying drawing content are made, or directly or indirectly it is used in other correlations
Technical field, be included within the scope of the present invention.
Claims (8)
1. a kind of multiple image clearness processing method, it is characterised in that comprise the following steps:
Pending image is carried out into pixel replicability amplification, the high-definition picture after being amplified;
The target signature in high-definition picture is chosen, change in location of the target signature in high-definition picture, and root is determined
According to change in location reduction target signature position, target signature is set to be in same position in high-definition picture;
By all high-definition picture additive fusions.
2. multiple image clearness processing method as claimed in claim 1, it is characterised in that described to carry out pending image
Pixel replicability is amplified, before the high-definition picture step after being amplified, including,
Video file is resolved into multiple images according to the frame number of itself, and is arranged in order according to image frame sequential.
3. multiple image clearness processing method as claimed in claim 1, it is characterised in that the selection high-definition picture
In target signature, determine change in location of the target signature in high-definition picture, and it is special to reduce target according to change in location
Position is levied, target signature is in same position step in high-definition picture, including,
High-definition picture after amplification is replicated, corresponding high-resolution sample image is obtained, to high-definition picture
Sample carries out Gaussian Blur computing or goes Gaussian Blur computing;
Latter two field picture is moved with reference to previous frame image, when the target signature center on image or edge contour are overlapped, record
The each change in location data of high-resolution sample image, and by change in location data migration to original high resolution image.
4. multiple image clearness processing method as claimed in claim 3, it is characterised in that described by all edge graphs
As fusion superposition step, including,
Position mobile data in high-definition picture, by the superposition of all image co-registrations.
5. a kind of multiple image sharpening processing unit, it is characterised in that including:
Amplifying unit, for pending image to be carried out into pixel replicability amplification, the high-definition picture after being amplified;
Position recovering unit, for choosing the target signature in high-definition picture, determines target signature in high-definition picture
In change in location, and target signature position is reduced according to change in location, be in target signature identical in high-definition picture
Position;
Additive fusion unit, for by all high-definition picture additive fusions.
6. multiple image sharpening processing unit as claimed in claim 1, it is characterised in that also include,
Pretreatment unit, for video file to be resolved into multiple images according to the frame number of itself, and according to image frame sequential
It is arranged in order.
7. multiple image sharpening processing unit as claimed in claim 1, it is characterised in that the position recovering unit, bag
Include,
Edge treated module, for the high-definition picture after amplification to be replicated, obtains corresponding high-resolution sample graph
Picture, carries out Gaussian Blur computing or goes Gaussian Blur computing to high-definition picture sample;
Displacement acquisition module, for moving latter two field picture with reference to previous frame image, when target signature center or side on image
When edge profile is overlapped, each change in location data of high-resolution sample image are recorded, and change in location data migration is arrived
Original high resolution image.
8. multiple image sharpening processing unit as claimed in claim 1, it is characterised in that the additive fusion unit, bag
Additive fusion module is included, for the position mobile data in high-definition picture, by the superposition of all image co-registrations.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611000429.6A CN106780354A (en) | 2016-11-14 | 2016-11-14 | Multiple image clearness processing method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611000429.6A CN106780354A (en) | 2016-11-14 | 2016-11-14 | Multiple image clearness processing method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106780354A true CN106780354A (en) | 2017-05-31 |
Family
ID=58971997
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611000429.6A Pending CN106780354A (en) | 2016-11-14 | 2016-11-14 | Multiple image clearness processing method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106780354A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110430376A (en) * | 2019-07-25 | 2019-11-08 | 西南交通大学 | A kind of image processing method and system |
CN113709372A (en) * | 2021-08-27 | 2021-11-26 | 维沃移动通信(杭州)有限公司 | Image generation method and electronic device |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101252686A (en) * | 2008-03-20 | 2008-08-27 | 上海交通大学 | Undamaged encoding and decoding method and system based on interweave forecast |
CN101272489A (en) * | 2007-03-21 | 2008-09-24 | 中兴通讯股份有限公司 | Encoding and decoding device and method for video image quality enhancement |
US20100086048A1 (en) * | 2008-10-03 | 2010-04-08 | Faisal Ishtiaq | System and Method for Video Image Processing |
CN102770887A (en) * | 2010-01-28 | 2012-11-07 | 耶路撒冷希伯来大学伊森姆研究发展有限公司 | Method and system for generating an output image of increased pixel resolution from an input image |
CN104063875A (en) * | 2014-07-10 | 2014-09-24 | 深圳市华星光电技术有限公司 | Super-resolution reconstruction method for enhancing smoothness and definition of video image |
CN104660951A (en) * | 2015-01-21 | 2015-05-27 | 上海交通大学 | Super-resolution amplification method of ultra-high definition video image converted from high definition video image |
CN105959700A (en) * | 2016-05-31 | 2016-09-21 | 腾讯科技(深圳)有限公司 | Video image coding method and device |
-
2016
- 2016-11-14 CN CN201611000429.6A patent/CN106780354A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101272489A (en) * | 2007-03-21 | 2008-09-24 | 中兴通讯股份有限公司 | Encoding and decoding device and method for video image quality enhancement |
CN101252686A (en) * | 2008-03-20 | 2008-08-27 | 上海交通大学 | Undamaged encoding and decoding method and system based on interweave forecast |
US20100086048A1 (en) * | 2008-10-03 | 2010-04-08 | Faisal Ishtiaq | System and Method for Video Image Processing |
CN102770887A (en) * | 2010-01-28 | 2012-11-07 | 耶路撒冷希伯来大学伊森姆研究发展有限公司 | Method and system for generating an output image of increased pixel resolution from an input image |
CN104063875A (en) * | 2014-07-10 | 2014-09-24 | 深圳市华星光电技术有限公司 | Super-resolution reconstruction method for enhancing smoothness and definition of video image |
CN104660951A (en) * | 2015-01-21 | 2015-05-27 | 上海交通大学 | Super-resolution amplification method of ultra-high definition video image converted from high definition video image |
CN105959700A (en) * | 2016-05-31 | 2016-09-21 | 腾讯科技(深圳)有限公司 | Video image coding method and device |
Non-Patent Citations (2)
Title |
---|
柯水洲等: "基于参考帧的视频播放超分辨率放大算法", 《计算机应用研究》 * |
韩玉兵: "一种视频序列的超分辨率重建算法", 《电子学报》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110430376A (en) * | 2019-07-25 | 2019-11-08 | 西南交通大学 | A kind of image processing method and system |
CN110430376B (en) * | 2019-07-25 | 2021-12-28 | 西南交通大学 | Image processing method and system |
CN113709372A (en) * | 2021-08-27 | 2021-11-26 | 维沃移动通信(杭州)有限公司 | Image generation method and electronic device |
CN113709372B (en) * | 2021-08-27 | 2024-01-23 | 维沃移动通信(杭州)有限公司 | Image generation method and electronic device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
DE112018002228B4 (en) | CONFIGURABLE CONVOLUTION ENGINE FOR NESTING CHANNEL DATA | |
US10929720B2 (en) | Image processing method, image processing apparatus, and computer storage medium | |
CN110969589B (en) | Dynamic scene blurred image blind restoration method based on multi-stream annotating countermeasure network | |
US7945114B2 (en) | Image transform method for obtaining expanded image data, image processing apparatus and image display device therefore | |
EP3200147B1 (en) | Image magnification method, image magnification apparatus and display device | |
US8704843B2 (en) | Image processing apparatus and image processing method | |
CN108109109B (en) | Super-resolution image reconstruction method, device, medium and computing equipment | |
CN102665557A (en) | X-ray image processing apparatus, x-ray image processing method, and storage medium for computer program | |
CN103559693A (en) | Image local structure self-adaption recovery method based on non-continuity indicator | |
CN104272347A (en) | Image processing apparatus for removing haze contained in still image and method thereof | |
CN104050642B (en) | Color image restoration method | |
CN106156691A (en) | The processing method of complex background image and device thereof | |
CN106780354A (en) | Multiple image clearness processing method and device | |
US20080002904A1 (en) | Adaptive image sharpening method | |
CN103971349B (en) | Computed tomography images method for reconstructing and ct apparatus | |
CN110415223B (en) | No-reference spliced image quality evaluation method and system | |
CN111986116A (en) | Video noise reduction method and device, electronic equipment and computer readable storage medium | |
Wang et al. | First image then video: a two-stage network for spatiotemporal video denoising | |
CN106780538A (en) | A kind of method of error hiding during solution image trace | |
CN107862670B (en) | Image restoration method for infrared imaging electric crosstalk | |
CN107103321B (en) | The generation method and generation system of road binary image | |
CN113038055B (en) | Image processing method and device and electronic equipment | |
US11423597B2 (en) | Method and system for removing scene text from images | |
US9754162B2 (en) | Image processing method and device for adaptive image enhancement | |
CN111292677B (en) | Image display processing method and device, computer equipment and storage medium |
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: 20170531 |
|
RJ01 | Rejection of invention patent application after publication |