基于结构张量的视频超分辨率算法

doi:10.11772/j.issn.1001-9081.2016.07.1944

计算机应用 ›› 2016, Vol. 36 ›› Issue (7): 1944-1948.DOI: 10.11772/j.issn.1001-9081.2016.07.1944

基于结构张量的视频超分辨率算法

严宏海, 卜方玲, 徐新

武汉大学电子信息学院, 武汉 430079

收稿日期:2015-12-24 修回日期:2016-03-14 出版日期:2016-07-10 发布日期:2016-07-14
通讯作者: 卜方玲
作者简介:严宏海(1991-),男,河南驻马店人,硕士研究生,主要研究方向:视频建模、超分辨率;卜方玲(1967-),女,湖北武汉人,副教授,博士,主要研究方向:系统与网络、信息处理;徐新(1967-),男,湖北武汉人,教授,博士生导师,博士,主要研究方向:遥感影像处理、语音信号处理、通信信号处理。
基金资助:
国家863计划项目（2013AA122301）。

Video super resolution method based on structure tensor

YAN Honghai, PU Fangling, XU Xin

School of Electronic Information, Wuhan University, Wuhan Hubei 430079, China

Received:2015-12-24 Revised:2016-03-14 Online:2016-07-10 Published:2016-07-14
Supported by:
This work is partially supported by the National High Technology Research and Development Program (863 Program) of China (2013AA122301).

摘要/Abstract

摘要： 针对传统正则化超分辨率（SR）重建模型中，正则化参数选择过大会使重建结果模糊，导致边缘和纹理等细节丢失，选择过小模型去噪能力又不足的问题，提出一种基于结构张量的双正则化参数的视频超分辨率重建算法。首先，利用局部结构张量对图像进行平滑区域和边缘的检测；然后，利用差异曲率对全变分（TV）进行先验信息加权；最后，对平滑区域和边缘采用不同的正则化参数进行超分辨率重建。实验数据显示提出的算法将峰值信噪比（PSNR）提高了0.033～0.11 dB，具有较好的重建效果。实验结果表明：该算法能够有效地提升低分辨率（LR）视频帧重建效果，可应用于低分辨率视频增强、车牌识别和视频监控中感兴趣目标增强等方面。

关键词: 超分辨率, 帧序列, 结构张量, 双正则化参数, 全变分加权

Abstract: The parameter of traditional regularized Super Resolution (SR) reconstruction model is difficult to choose:the higher parameter value results in blurred reconstruction and the fading of edge and detail, while the lower parameter value weakens the denosing ability. A double regularization parameters super resolution reconstruction method based on structure tensor was proposed. Firstly, smooth region and edge was detected by using local structure tensor. Secondly, the Total Variation (TV) was weighted with the priori information of difference curvature. Finally, two different parameters toward smooth region and edge were used to reconstruct super resolution image. The experimental data show that the proposed algorithm can improve the Peak Signal-to-Noise Ratio (PSNR) of 0.033-0.11 dB, and get better reconstruction results. The proposed algorithm can effectively improve the reconstruction effect of Low Resolution (LR) video frames, and can be applied to LR video enhancement, license plate recognition and the interest target enhancement in video surveillance, etc.

Key words: Super Resolution (SR), frame sequence, structure tensor, double regularization parameter, Total Variation (TV) weighting

中图分类号:

严宏海, 卜方玲, 徐新. 基于结构张量的视频超分辨率算法[J]. 计算机应用, 2016, 36(7): 1944-1948.

YAN Honghai, PU Fangling, XU Xin. Video super resolution method based on structure tensor[J]. Journal of Computer Applications, 2016, 36(7): 1944-1948.

参考文献

[1] PARK S C, PARK M K, KANG M G. Super-resolution image reconstruction:a technical overview[J]. IEEE Signal Processing Magazine, 2003, 20(4):21-36.
[2] BLOMGREN P, CHAN T F, MULET P, et al. Total variation image restoration:numerical methods and extensions[C]//Proceedings of IEEE 1997 International Conference on Image Processing. Piscataway, NJ:IEEE, 1997, 3:384-387.
[3] ELAD M, FEUER A. Restoration of a single superresolution image from several blurred, noisy, and undersampled measured images[J]. IEEE Transactions on Image Processing, 1997, 6(12):1646-1658.
[4] CHAN T F, OSHER S, SHEN J. The digital TV filter and nonlinear denoising[J]. IEEE Transactions on Image Processing, 2001, 10(2):231-241.
[5] FARSIU S, ROBINSON M D, ELAD M, et al. Fast and robust multiframe super resolution[J]. IEEE Transactions on Image Processing, 2004, 13(10):1327-1344.
[6] YUAN Q, ZHANG L, SHEN H. Multiframe super-resolution employing a spatially weighted total variation model[J]. IEEE Transactions on Circuits & Systems for Video Technology, 2012, 22(3):379-392.
[7] SONG H, QING L, WU Y, et al. Adaptive regularization-based space-time super-resolution reconstruction[J]. Signal Processing:Image Communication, 2013, 28(7):763-778.
[8] BERTACCINI D, CHAN R H, MORIGI S, et al. An adaptive norm algorithm for image restoration[C]//SSVM'11:Proceedings of the Third International Conference on Scale Space and Variational Methods in Computer Vision, LNCS 6667. Berlin:Springer, 2011:194-205.
[9] ZHANG X, XIONG R, MA S, et al. Video super-resolution with registration-reliability regulation and adaptive total variation[J]. Journal of Visual Communication and Image Representation, 2015, 30:181-190.(无期号)
[10] LI X, HU Y, GAO X, et al. A multi-frame image super-resolution method[J]. Signal Processing, 2010, 90(2):405-414.
[11] QIANG C, MONTESINOS P, QUAN S S, et al. Adaptive total variation denoising based on difference curvature[J]. Image & Vision Computing, 2010, 28(3):298-306.
[12] BROX T, WEICKERT J, BURGETH B, et al. Nonlinear structure tensors[J]. Image & Vision Computing, 2006, 24(1):41-55.
[13] BOUGUET J Y. Pyramidal implementation of the Lucas Kanade feature tracker description of the algorithm[EB/OL].[2015-12-10]. http://robots.stanford.edu/cs223b04/algo_tracking.pdf.
[14] HUYNH-THU Q, GHANBARI M. Scope of validity of PSNR in image/video quality assessment[J]. Electronics Letters, 2008, 44(13):800-801.
[15] WANG Z, BOVIK A C, SHEIKH H R, et al. Image quality assessment:from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4):600-612.
[16] LIN Z, LEI Z, XUANQIN M, et al. FSIM:a feature similarity index for image quality assessment[J]. IEEE Transactions on Image Processing, 2011, 20(8):2378-2386.

基于结构张量的视频超分辨率算法

Video super resolution method based on structure tensor

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	牛康力, 谌雨章, 沈君凤, 曾张帆, 潘永才, 王绎冲. 基于深度学习的双通道夜视图像复原方法[J]. 计算机应用, 2021, 41(6): 1775-1784.
[2]	梁敏, 王昊榕, 张瑶, 李杰. 基于加速残差网络的图像超分辨率重建方法[J]. 计算机应用, 2021, 41(5): 1438-1444.
[3]	段友祥, 张含笑, 孙歧峰, 孙友凯. 基于拉普拉斯金字塔生成对抗网络的图像超分辨率重建算法[J]. 计算机应用, 2021, 41(4): 1020-1026.
[4]	卞鹏程, 郑忠龙, 李明禄, 何依然, 王天翔, 张大伟, 陈丽媛. 基于注意力融合网络的视频超分辨率重建[J]. 计算机应用, 2021, 41(4): 1012-1019.
[5]	王永金, 左羽, 吴恋, 崔忠伟, 赵晨洁. 基于注意力机制的图像超分辨率重建[J]. 计算机应用, 2021, 41(3): 845-850.
[6]	孙琳, 袁玉波. 基于人眼状态的瞌睡识别算法[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3213-3218.
[7]	李萌, 秦品乐, 曾建潮, 李俊伯. 基于磁共振影像层间插值的超分辨率及多视角融合[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3362-3367.
[8]	林静, 黄玉清, 李磊民. 基于球形矩匹配与特征判别的图像超分辨率重建[J]. 计算机应用, 2020, 40(8): 2345-2350.
[9]	胡高鹏, 陈子鎏, 王晓明, 张开放. 基于深度渐进式反投影注意力网络的图像超分辨率重建[J]. 计算机应用, 2020, 40(7): 2077-2083.
[10]	胡雪影, 郭海儒, 朱蓉. 基于混合深度卷积网络的图像超分辨率重建[J]. 计算机应用, 2020, 40(7): 2069-2076.
[11]	代强, 程曦, 王永梅, 牛子未, 刘飞. 基于轻量自动残差缩放网络的图像超分辨率重建[J]. 计算机应用, 2020, 40(5): 1446-1452.
[12]	陈赛健, 朱远平. 基于生成对抗网络的文本图像联合超分辨率与去模糊方法[J]. 计算机应用, 2020, 40(3): 859-864.
[13]	孙忠凡, 周正华, 赵建伟. 基于空间元学习的放大任意倍的超分辨率重建方法[J]. 计算机应用, 2020, 40(12): 3471-3477.
[14]	樊帆, 高媛, 秦品乐, 王丽芳. 基于并行通道-空间注意力机制的腹部MRI影像多尺度超分辨率重建[J]. 计算机应用, 2020, 40(12): 3624-3630.
[15]	叶杨, 蔡琼, 杜晓标. 基于非局部通道注意力机制的单图像超分辨率方法[J]. 计算机应用, 2020, 40(12): 3618-3623.