CN102905138A - High-resolution reconstruction method of video - Google Patents
High-resolution reconstruction method of video Download PDFInfo
- Publication number
- CN102905138A CN102905138A CN2011102109185A CN201110210918A CN102905138A CN 102905138 A CN102905138 A CN 102905138A CN 2011102109185 A CN2011102109185 A CN 2011102109185A CN 201110210918 A CN201110210918 A CN 201110210918A CN 102905138 A CN102905138 A CN 102905138A
- Authority
- CN
- China
- Prior art keywords
- resolution
- video
- continuous
- images
- field picture
- 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
Images
Landscapes
- Television Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a high-resolution reconstruction method of a video. The method comprises the following steps of: step 1) sequentially marking a video flow as N continuous frames of images, wherein N is a positive integer; step 2) sequentially selecting n continuous frames of images from the N continuous frames of images, utilizing a super-resolution technology to obtain a reconstructed frame of image, then moving one frame backwards, taking n continuous frames of images, further generating one frame of high-resolution image, and operating sequentially to generate high-resolution images by utilizing a production line form, wherein N is more than n, and n is more than 1; and step 3) sequentially playing a series of the obtained continuous new high-resolution images to obtain a high-resolution video. According to the method disclosed by the invention, the change for the spatial resolution by time bandwidth is overcome, and the change for the spatial resolution without cost is realized; and furthermore, the implementation processes are simple, and the method is suitable for various video products.
Description
Technical field
The present invention relates to computer technology, image recognition processing technical field, be specifically related to a kind of method of video super-resolution reconstruction.
Background technology
The detailed information that the image of low resolution comprises is less, but we can obtain the image of a series of low resolution, and the part detailed information that these images comprise is had nothing in common with each other, and can mutually replenish.By the image of these a series of low resolutions, the processing through certain can obtain an image that width of cloth resolution is higher, inclusion information is more.This processing procedure is exactly image super-resolution rebuilding.
The core concept of image super-resolution rebuilding uses time bandwidth (obtaining the multiple image sequence of Same Scene) to exchange spatial resolution for exactly, realizes that temporal resolution is to the conversion of spatial resolution.
How to break the thought that exchanges spatial resolution with the time bandwidth for, realize the spatial resolution that exchanges for free of charge, also do not have at present correlation technique to occur.
Summary of the invention
For overcoming deficiency of the prior art, the present invention aims to provide a kind of method that exchanges the video super-resolution reconstruction of spatial resolution for free of charge that realizes.
For realizing above-mentioned technical purpose, reach above-mentioned technique effect, the present invention is achieved through the following technical solutions:
A kind of method of video super-resolution reconstruction, it may further comprise the steps:
Step 1) be continuous N two field picture with the video flowing sequence notation, N is positive integer;
Step 2) order is chosen the two field picture that continuous n two field picture utilizes super-resolution technique to obtain rebuilding from continuous N two field picture, then move afterwards a frame and get again continuous n two field picture regeneration one vertical frame dimension image in different resolution, by that analogy, utilize the form of streamline sequentially to generate successively high-resolution image, 1＜n＜N;
A series of continuous new high-definition picture played in order that step 3) will obtain have namely obtained high-resolution video.
Compared with prior art, the present invention has following beneficial effect:
The present invention has overcome with the time bandwidth and has exchanged spatial resolution for, realize the spatial resolution that exchanges for free of charge, and implementation procedure is simple, applicable to various video products.
Above-mentioned explanation only is the general introduction of technical solution of the present invention, for can clearer understanding technological means of the present invention, and can be implemented according to the content of specification, below with preferred embodiment of the present invention and cooperate accompanying drawing to be described in detail as follows.The specific embodiment of the present invention is provided in detail by following examples and accompanying drawing thereof.
Description of drawings
Accompanying drawing described herein is used to provide a further understanding of the present invention, consists of the application's a part, and illustrative examples of the present invention and explanation thereof are used for explaining the present invention, do not consist of improper restriction of the present invention.In the accompanying drawings:
Fig. 1 is realization flow schematic diagram of the present invention.
Fig. 2 is the schematic flow sheet of one embodiment of the invention.
Embodiment
Below with reference to the accompanying drawings and in conjunction with the embodiments, describe the present invention in detail.
Referring to shown in Figure 1, a kind of method of video super-resolution reconstruction, it may further comprise the steps:
Step 1) be continuous N two field picture with the video flowing sequence notation, N is positive integer;
Step 2) order is chosen the two field picture that continuous n two field picture utilizes super-resolution technique to obtain rebuilding from continuous N two field picture, then move afterwards a frame and get again continuous n two field picture regeneration one vertical frame dimension image in different resolution, by that analogy, utilize the form of streamline sequentially to generate successively high-resolution image, 1＜n＜N;
A series of continuous new high-definition picture played in order that step 3) will obtain have namely obtained high-resolution video.
Referring to shown in Figure 2, preferred n gets 3.
The above is the preferred embodiments of the present invention only, is not limited to the present invention, and for a person skilled in the art, the present invention can have various modifications and variations.Within the spirit and principles in the present invention all, any modification of doing, be equal to replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (1)
1. the method for a video super-resolution reconstruction is characterized in that, may further comprise the steps:
Step 1) be continuous N two field picture with the video flowing sequence notation, N is positive integer;
Step 2) order is chosen the two field picture that continuous n two field picture utilizes super-resolution technique to obtain rebuilding from continuous N two field picture, then move afterwards a frame and get again continuous n two field picture regeneration one vertical frame dimension image in different resolution, by that analogy, utilize the form of streamline sequentially to generate successively high-resolution image, 1＜n＜N;
A series of continuous new high-definition picture played in order that step 3) will obtain have namely obtained high-resolution video.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011102109185A CN102905138A (en) | 2011-07-27 | 2011-07-27 | High-resolution reconstruction method of video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011102109185A CN102905138A (en) | 2011-07-27 | 2011-07-27 | High-resolution reconstruction method of video |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102905138A true CN102905138A (en) | 2013-01-30 |
Family
ID=47577152
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011102109185A Pending CN102905138A (en) | 2011-07-27 | 2011-07-27 | High-resolution reconstruction method of video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102905138A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108665411A (en) * | 2018-03-09 | 2018-10-16 | 北京超维景生物科技有限公司 | A kind of method and system of image reconstruction |
| CN110166795A (en) * | 2018-07-19 | 2019-08-23 | 腾讯科技（深圳）有限公司 | A kind of video interception method and device |
| CN110418198A (en) * | 2019-06-30 | 2019-11-05 | 联想(北京)有限公司 | A kind of video information processing method, electronic equipment and storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101917624A (en) * | 2010-07-26 | 2010-12-15 | 清华大学 | A High Resolution Video Image Reconstruction Method |
-
2011
- 2011-07-27 CN CN2011102109185A patent/CN102905138A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101917624A (en) * | 2010-07-26 | 2010-12-15 | 清华大学 | A High Resolution Video Image Reconstruction Method |
Non-Patent Citations (3)
| Title |
|---|
| BALAJI NARAYANAN EA TL.: "A Computationally Efficient Super-Resolution Algorithm for Video Processing Using Partition Filters", 《IEEE TRANSACTIONS CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY》, vol. 17, no. 5, 31 May 2007 (2007-05-31) * |
| 吴媛媛 等: "基于小波局部适应插值IBP算法的视频超分辨率重建", 《四川大学学报（自然科学版）》, vol. 48, no. 2, 31 March 2011 (2011-03-31) * |
| 曹聚亮 等: "基于实时帧迭代反向投影算法的图像序列超分辨率处理", 《光学技术》, vol. 30, no. 5, 30 September 2004 (2004-09-30) * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108665411A (en) * | 2018-03-09 | 2018-10-16 | 北京超维景生物科技有限公司 | A kind of method and system of image reconstruction |
| CN108665411B (en) * | 2018-03-09 | 2022-05-24 | 广州超视计生物科技有限公司 | Image reconstruction method and system |
| CN110166795A (en) * | 2018-07-19 | 2019-08-23 | 腾讯科技（深圳）有限公司 | A kind of video interception method and device |
| CN110418198A (en) * | 2019-06-30 | 2019-11-05 | 联想(北京)有限公司 | A kind of video information processing method, electronic equipment and storage medium |
| CN110418198B (en) * | 2019-06-30 | 2021-05-18 | 联想(北京)有限公司 | Video information processing method, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhu et al. | Cross view capture for stereo image super-resolution | |
| CN109671023B (en) | A Super-resolution Reconstruction Method of Face Image | |
| CN110226316B (en) | System and method for converting and streaming virtual reality video | |
| CN110634105B (en) | A video signal processing method with high spatio-temporal resolution combining optical flow method and deep network | |
| CN102111613B (en) | Image processing method and device | |
| CN101477684A (en) | Process for reconstructing human face image super-resolution by position image block | |
| Chen et al. | Compressed domain deep video super-resolution | |
| CN103248797A (en) | Video resolution enhancing method and module based on FPGA (field programmable gate array) | |
| CN103279320A (en) | Method for performing interactive display of multiple different-resolution screens of interactive projection system | |
| CN107613299A (en) | A Method of Using Generative Networks to Improve Frame Rate Upconversion | |
| EP2661082A1 (en) | Method and device for rounding coordinate value of non-full pixel position motion vector | |
| CN114692765A (en) | Video spatio-temporal hyper-resolution model construction method, device, equipment and readable storage medium | |
| CN102905138A (en) | High-resolution reconstruction method of video | |
| JP2013519296A5 (en) | ||
| CN118052707A (en) | Light-weight super-resolution reconstruction method based on local and global interaction fusion of Transformer | |
| CN102790895B (en) | Multi-viewpoint video encoding and viewpoint synthesis predication method based on least square | |
| CN102026012B (en) | Generation method and device of depth map through three-dimensional conversion to planar video | |
| CN102769732B (en) | A kind of conversion method for realizing video field | |
| WO2023138226A1 (en) | Sending card and receiving card for display system, display control method, and storage medium | |
| CN104168471A (en) | Sub-pixel coding-based integrated imaging display apparatus and realization method thereof | |
| CN103310431B (en) | A kind of based on hardware-accelerated Single Infrared Image Frame ultra-resolution method | |
| CN103400394B (en) | Feature based guides the video super-resolution method of variation light stream | |
| CN103903240A (en) | Image super-resolution method based on multi-output least square support vector regression | |
| CN103686029B (en) | A kind of video pixel opposite-angle interpolation method for the many optical projection systems of giant-screen | |
| CN102111636A (en) | Method and system for converting three-dimensional (3D) signal into two-dimensional (2D) signal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C05 | Deemed withdrawal (patent law before 1993) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20130130 |