非局部低秩正则化视频压缩感知重构
作者:
作者单位:

上海大学

作者简介:

通讯作者:

中图分类号:

TN911.73

基金项目:


Video Compressive Sensing Reconstruction via Nonlocal Low-Rank Regularization
Author:
Affiliation:

Shanghai University

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    视频压缩感知在采样资源受限的视频采集领域具有重要研究意义,重构算法是视频压缩感知系统的关键技术.为了更好地从压缩采样数据中重构视频信号,本文提出一种基于全变分与非局部低秩正则化的视频重构算法,为视频重构提供一种新的思路.该算法包括两个步骤:第一步考虑视频帧内局部光滑特性和帧间相关性,应用全变分模型作为先验约束得到初步恢复的视频帧.第二步考虑视频帧内和帧间的非局部自相似性,应用改进的非局部低秩正则化算法对其进一步重构,该步骤对初步恢复的图像帧分块,在本帧和关键帧中寻找相似块,构建低秩矩阵进行低秩正则化重构.仿真结果表明,提出的算法能够精确重构视频信号,相比主流的视频压缩感知重构算法具有更高的重构质量.

    Abstract:

    Compressive video sensing (CVS) has great research significance in the video acquisition system with limited sampling resources. In this paper, we proposed a reconstruction algorithm based on total variation (TV) and nonlocal low-rank regularization (NLR-CS) to better reconstruct video signal from compressive sampled data. This algorithm consists two steps: The first step considers local correlation between and within video frames, applies TV as the prior constraint to obtain the initial recovered frame; In the second step, the improved NLR-CS algorithm is utilized to further reconstruct video frame considering the nonlocal self-similarity (NLSS). This step first blocks the initial recovered frame, finds similar blocks in the current frame and the key frames to construct low-rank matrix, then a low-ranking regularization reconstruction is performed. Experimental results show that the proposed algorithm can reconstruct video signals well, obtains higher video reconstruction accuracy than other CVS reconstruction algorithms.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2020-03-19
  • 最后修改日期:2021-06-25
  • 录用日期:2020-08-28
  • 在线发布日期: 2020-10-02
  • 出版日期: