多视频超分辨率的时间重建倍数

陈为龙; 郭黎; 雷刚; 吴炜; 杨晓敏

doi:10.3788/OPE.20142209.2518

您当前的位置：

首页 >

文章列表页 >

多视频超分辨率的时间重建倍数

信息科学 | 更新时间：2020-08-13

- 多视频超分辨率的时间重建倍数
- Temporal reconstruction times of video-to-video super-resolution
- 光学精密工程 2014年22卷第9期页码：2518-2527
- 作者机构：
  
  1. 四川大学电子信息学院,四川成都,610065
  2. 四川师范大学数字媒体学院,四川成都,610068
  3. 湖北民族学院信息工程学院,湖北恩施,445000
- 作者简介：
- 基金信息：
  
  四川省教育厅科学研究项目（No.11ZB073）();可视化计算与虚拟现实四川省重点实验室资助项目（No.PJ201113）();湖北省自然科学基金资助项目（No.20
- DOI：10.3788/OPE.20142209.2518
  中图分类号： TN911.73;TP391.9
- 收稿日期：2013-12-10，
  
  修回日期：2014-02-02，
  
  纸质出版日期：2014
- 稿件说明：
移动端阅览
陈为龙, 郭黎, 雷刚等. 多视频超分辨率的时间重建倍数[J]. 光学精密工程, 2014,22(9): 2518-2527

CHEN Wei-long, GUO Li, LEI Gang etc. Temporal reconstruction times of video-to-video super-resolution[J]. Editorial Office of Optics and Precision Engineering, 2014,22(9): 2518-2527
陈为龙, 郭黎, 雷刚等. 多视频超分辨率的时间重建倍数[J]. 光学精密工程, 2014,22(9): 2518-2527 DOI： 10.3788/OPE.20142209.2518.

CHEN Wei-long, GUO Li, LEI Gang etc. Temporal reconstruction times of video-to-video super-resolution[J]. Editorial Office of Optics and Precision Engineering, 2014,22(9): 2518-2527 DOI： 10.3788/OPE.20142209.2518.

摘要

多视频超分辨率时间重建技术可以消除视频中的运动模糊和运动混叠现象。进行多视频时间重建时，重建倍数过小不能有效地减小运动模糊和运动混叠现象；而重建倍数过大会产生严重的时间振铃现象和运动物体位置的跳变。本文对如何在重建过程中确定最优的时间重建倍数进行了研究。通常情况下，在决定多视频时间重建倍数时只考虑输入视频的个数；但在实际重建过程中，除了输入视频个数的因素，时间重建倍数还与各个输入视频在时间上能提供的冗余信息量有关。文中从多个低分辨率输入视频配准后的位置关系入手，通过对曝光区间的分析，提出了确定多视频时间重建倍数的计算方法。最后对提出的方法进行了理论分析与实验，证明了所提方法的有效性。

Abstract

Video-to-video temporal super-resolution technology eliminates motion blur and motion aliasing existing in a captured video sequence. However

smaller temporal reconstruction times can not effectively remove motion blur and motion aliasing

while larger times will lead to serious temporal-ringing and the wrong location of a moving object in process of temporal reconstruction. This paper explores how to select an appropriate temporal construction times in the temporal reconstruction. In general

only the number of input video sequences is considered in deciding temporal reconstruction times of video-to-video super-resolution reconstruction. In fact

temporal reconstruction times are also associated with redundant temporal information provided by each input low-temporal resolution video sequence. So

a novel method to select an appropriate temporal reconstruction times is proposed by analyzing the exposure-time and location relation of aligned low resolution input video sequences. From theoretical discussion and experimental results

the proposed method is validated to be effective and efficient.

关键词

Keywords

references

MUDENAGUDI U, BANERJEE S, KALRA P K. Space-time super-resolution using graph-cut optimization [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(5):995-1008.

AGRAWAL A, GUPTA M, VEERARAGHAVAN A.Optimal coded sampling for temporal super resolution [J]. In Proc. IEEE CVPR, 2010:599-606.

彭晓明, 丁明跃, 周成平,等. 一种序列图像配准的计算框架[J]. 中国图象图形学报, 2005, 10(4):441-449. PENG X M, DING M Y, ZHOU CH P, et al.. A computational framework for the temporal-spatial alignment of multi-sensor image sequences [J]. Journal of Image and Graphics, 2005, 10(4):441-449. (in Chinese)

SHECHTMAN E, CASPI Y, IRANI M. Space-time super-resolution [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(4):531-544.

CASPI Y, IRANI M. Spatio-temporal alignment of sequences [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2002, 24(11):1409-1419.

CASPI Y, IRANI M. Aligning non-overlapping sequences [J]. International Journal of Computer Vision, 2002, 48(1):39-51.

CASPI Y. Sequence-to-sequence alignment [D]. Scientific Council of the Weizman Institute of Science Rehovot, Israel, 2002.

覃风清, 何小海, 陈为龙,等. 一种图像配准的超分辨率重建[J]. 光学精密工程, 2009,17(2):409-416. QIN F Q, HE X H, CHEN W L, et al.. Super-resolution reconstruction method of image registration [J]. Opt.Precision Eng., 2009,17(2):409-416. (in Chinese)

张进,王仲, 李雅洁,等. 高精度影像测量系统中图像的超分辨率重建[J]. 光学精密工程, 2011,19(1):168-174. ZHANG J, WANG ZH, LI Y J, et al.. Super-resolution reconstruction of image in high accuracy image measuring system [J]. Opt.Precision Eng., 2011, 19(1):168-174. (in Chinese)

李家德, 张叶, 贾平. 采用非局部均值的超分辨率重构[J]. 光学精密工程, 2013, 21(6):1576-1585. LI J D, ZHANG Y, JIA P. Super-resolution reconstruction using nonlocal means [J]. Opt.Precision Eng., 2013, 21(6):1576-1585. (in Chinese)

张地,何家忠. 基于特征空间的人脸超分辨率重构[J]. 自动化学报, 2012,38(7):1145-1152. ZHANG D, HE J ZH. Feature space based face super-resolution reconstruction [J]. Acta Automatica Sinica, 2012,38(7):1145-1152. (in Chinese)

CHEN W L, HE X H, SONG H Y. An improved sequence-to-sequence alignment method combined with feature-based image registration algorithm [J]. Journal of Information Science and Engineering, 2012, 28(3):617-630.

张元,钟兴,金光,等. 基于CCD阵列错排的图像差分超分辨重建方法[J]. 液晶与显示,2011,26(6):841-846. ZHANG Y, ZHONG X, JING G, et al.. Super resolution reconstruction of image difference based on CCD staggered arrays [J]. Chinese Journal of Liquid Crystals and Displays, 2011,26(6):841-846. (in Chinese)

浏览量

668

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

优化预测运动矢量的快速运动估计算法