[1]卢 涛,章 瑾,陈白帆,等.多尺度自适应配准的视频超分辨率算法[J].武汉工程大学学报,2016,38(2):178-184.[doi:10. 3969/j. issn. 1674-2869. 2016. 02. 014]
LU Tao,ZHANG Jin,CHEN Baifan,et al.Video Super-Resolution Algorithm Via multi-Scale Adaptive Block-Matching Registration[J].Journal of Wuhan Institute of Technology,2016,38(2):178-184.[doi:10. 3969/j. issn. 1674-2869. 2016. 02. 014]
点击复制
《武汉工程大学学报》[ISSN:1674-2869/CN:42-1779/TQ]
- 卷:
-
38
- 期数:
-
2016年2期
- 页码:
-
178-184
- 栏目:
-
机电与信息工程
- 出版日期:
-
2016-04-30
文章信息/Info
- Title:
-
Video Super-Resolution Algorithm Via multi-Scale Adaptive Block-Matching Registration
- 作者:
-
卢 涛1; 2 ; 章 瑾1; 2; 陈白帆3; 管英杰1; 2
-
1. 武汉工程大学计算机科学与工程学院,湖北 武汉 430205;
2. 智能机器人湖北省重点实验室(武汉工程大学),湖北 武汉 430205;
3. 中南大学信息科学与工程学院,湖南 长沙 410083
- Author(s):
-
LU Tao1; 2; ZHANG Jin1; 2; CHEN Baifan3; GUAN Yingjie1; 2
-
1. School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan 430205, China,;
2. Hubei Key Laboratory of Intelligent Robot (Wuhan Institute of Technology), Wuhan 430205, China;
3. School of Information Science and Engineering, Central South University, Changsha 410083, China
-
- 关键词:
-
视频超分辨率; 多尺度块匹配; 自适应配准
- Keywords:
-
video super-resolution; multi-scale block matching; adaptive registration
- 分类号:
-
TP391.4
- DOI:
-
10. 3969/j. issn. 1674-2869. 2016. 02. 014
- 文献标志码:
-
A
- 摘要:
-
为了提升制约视频超分辨率重建质量的多帧配准精度,提出了一种基于图像块多尺度自适应配准的视频超分辨率算法. 依据图像帧的块内容自适应选择配准尺度,运动边缘信息采用高精度配准,然后将运动向量补偿到多帧图像超分辨率重建代价函数中,利用最大后验概率算法迭代优化高分辨率视频帧. 仿真表明:多尺度自适应配准算法不仅提高了配准精度,还提升了视频超分辨率重建图像帧的主客观质量,证明了多尺度自适应配准在视频超分辨率重建中的有效性.
- Abstract:
-
To improve the registration accuracy which influences the performance of video super-resolution algorithms, we proposed a video super-resolution algorithm based on multi-scale adaptive block-matching registration. Registration scale was selected with block contents and the moving edge information of video was represented in high registration accuracy. Then, the registration motion vectors were compensated into the cost function of multi-frame super-resolution, and the high-resolution outputs frames were iteratively optimized by the algorithm of maximum a posteriori estimation. Simulation results show that the adaptive multi-scale registration not only enhances the accuracy of video registration, but also improves the performance of video super-resolution, which demonstrates the validity of adaptive multi-scale registration in video super-resolution reconstruction.
参考文献/References:
[1] 张新民,沈兰荪. 超分辨率复原技术的发展[J]. 测控技术,2002,5(22):33-35.
ZHANG X M, SHEN L S. The development of super-resolution restoration from image sequences[J].Measurement & control technology, 2002, 5(22):33-35.
[2] KANADE T, BAKER S. Limits on super-resolution and how to break them[J]. IEEE transactions on pattern analysis and machine intelligence,2002,24(9):1167- 1183.
[3] TSAI R Y, HUANG T S. Multiframe image restoration and registration[M]. Greenwich USA:JAI Press Inc,1984.
[4] PATTI A J, SEZAN M I, TEKALP A M. Super-resolution video reconstruction with arbitrary sampling lattices and nonzero aperture time[J]. IEEE transactions on image processing, 1997, 6 (8):1064-1076.
[5] SCHUILTZ R R, STEVENSON R L. Extraction of high resolution frames from video sequences[J]. Image processing,IEEE transactions on,1996,5(6):996-1011.
[6] MITZEL D, POCK T, SCHOENEMANN T. Pattern recognition[M]. Jena, Germany: Springer Berlin Heidelberg,2009.
[7] BISHOP C M, BLAKE A, MARTHI B. Patch-based video super-resolution: US,US 7218796 B2[P]. 2007-05-15.
[8] CE L, DEQING S. On bayesian adaptive video super resolution[J]. IEEE transaction on pattern analysis and machine intelligence,2014,36(2):346-360.
[9] ELAD M, FEUER A. Restoration of a single super-resolution image from several blured, noisy and undersampled measured images[J]. IEEE transactions on image, 1997, 6(12):1646-1658.
[10] KEREN D, PELEG S, BRADA R. Image sequence enhancement using sub-pixel displacements [C]// Computer Vision and Pattern Recognition. Proceedings CVPR’88. Computer Society. Comference on IEEE 1988:724-746 .
[11] BAKER S, KANADE T. Super-resolution optical flow[M]. Ann Arbor Michigan :IEEE,1999.
[12] TIKHONOV A N.Regularization of incorrectly posed problems[J]. Sov math,1963(4):1624-1627.
[13] FARSIU S,ELAD M,MILANFAR P. Multiframe demosaicing and super-resolution of color images[J]. IEEE transactions on image processing,2006,15(1):141-159.
更新日期/Last Update:
2016-05-03