| 基于稀疏编码的视频序列超分辨率重构 |
| |
| 引用本文： | 黄芳,邓宸伟,张元俊,赵保军,王文正.基于稀疏编码的视频序列超分辨率重构[J].电子技术,2014(1):5-7,4. |
| |
| 作者姓名： | 黄芳 邓宸伟 张元俊 赵保军 王文正 |
| |
| 作者单位： | [1]北京理工大学信息与电子学院 [2]北京邮电大学电子工程学院 |
| |
| 摘 要： | 把学习型算法用于稀疏编码的重建算法中来实现视频序列图像的超分辨率重构。该算法无需显式求取运动向量,能够克服传统方法对精确运动估计的要求,通过稀疏编码便能够自动利用邻近帧中最相关的那些样本块进行重构;另外,算法通过设置最大运动窗口,利用帧间运动的连续性特点,在相邻帧已经重建的基础上,提取其运动窗口内的高、低分辨率图像块来构建样本库,从而实现减小所需样本库的尺寸的目的。
|
| 关 键 词： | 图像超分辨率重构 样本学习 稀疏编码 稀疏字典 |
Video Super-Resolution Reconfiguration Based On Sparse Coding |
| |
| Huang Fang Deng Chenwei Zhang Yuanjun Zhao Baojun Wang Wenzheng.Video Super-Resolution Reconfiguration Based On Sparse Coding[J].Electronic Technology,2014(1):5-7,4. |
| |
| Authors: | Huang Fang Deng Chenwei Zhang Yuanjun Zhao Baojun Wang Wenzheng |
| |
| Institution: | Huang Fang Deng Chenwei Zhang Yuanjun Zhao Baojun Wang Wenzheng ( 1.School of Information and Electronics, Beijing Institute of Technology 2. School of Electronic Engineering, Beijing University of Posts and Telecommunications) |
| |
| Abstract: | The paper adopts learning algorithm into the reconfiguration algorithm for spare coding to realize a super resolution （SR） reconfiguration of the video sequence images. This method doesn＇t need explicit motion estimation, can overcome the demand for explicit motion estimation in traditional methods. By using the sparse coding technique, the method can automatically make use of the most related patch samples in the adjacent frames when reconstructing. Moreover, the method sets the maximum motion window for each location, utilizes the continuity feature of the inter-frame motions, and extracts the high resolution （HR） patches and low resolution （LR） versions in the adjacent frame within this window on the basis of adjacent frames having reconfigured to form the corresponding database, thereby reducing the necessary size of the database. |
| |
| Keywords: | image super-resolution （SR） reconfiguration learning sample sparse coding sparse dictionary |
| 本文献已被 CNKI 维普 等数据库收录！ |
|
