基于最大后验概率的单视频时间超分辨率重建算法

计算机应用 ›› 2014, Vol. 34 ›› Issue (12): 3580-3584.

基于最大后验概率的单视频时间超分辨率重建算法

郭黎¹,廖宇¹,陈为龙²,廖红华¹,李军¹,向军¹

1. 湖北民族学院信息工程学院,湖北恩施 445000
2. 四川师范大学数字媒体学院,成都 610068

收稿日期:2014-06-24 修回日期:2014-08-25 出版日期:2014-12-01 发布日期:2014-12-31
通讯作者: 郭黎
作者简介:郭黎(1978-),女,湖北黄冈人,讲师,博士,主要研究方向:视频图像处理与识别、数字媒体与信息显示；廖宇(1979-),男(土家族）,湖北建始人,讲师,博士研究生,主要研究方向:信号与信息处理、光通信；陈为龙(1981-),男,四川内江人,副教授,博士,主要研究方向:图像处理、超分辨率重建；廖红华(1972-),男(土家族）,湖北恩施人,副教授,博士,主要研究方向:微电子与固体电子学；信号处理与分析;李军(1972-),男(土家族）,湖北恩施人,教授,主要研究方向:计算机图形图像处理、虚拟现实技术、非物质文化遗产数字化保护;向军(1978-),男(土家族）,湖北来凤人,副教授,博士,主要研究方向:现代数据库理论、信息处理、软件测试
基金资助:
国家自然科学基金资助项目;国家自然科学基金;湖北省自然科学基金;湖北省教育厅优秀中青年人才项目;文化部创新项目;国家文化科技提升项目

Single video temporal super-resolution reconstruction algorithm based on maximum a posterior

GUO Li¹,LIAO Yu¹,CHEN Weilong²,LIAO Honghua¹,LI Jun¹,XIANG Jun¹

1. School of Information Engineering, Hubei University for Nationalities, Enshi Hubei 445000, China;
2. College of Digital Media, Sichuan Normal University, Chengdu Sichuan 610068,China

Received:2014-06-24 Revised:2014-08-25 Online:2014-12-01 Published:2014-12-31
Contact: GUO Li

摘要/Abstract

摘要：

任何视频摄像设备均具有一定的时间分辨率限制,时间分辨率不足会造成视频中存在运动模糊和运动混叠现象。针对这一问题常用的解决方法是空间去模糊和时间插值,然而这些方法无法从根本上解决问题。提出一种基于最大后验概率(MAP)的单视频时间超分辨率重建方法,该方法通过重建约束来确定条件概率模型,然后利用视频自身具有的时间自相似先验信息得到先验信息模型,最后求得基于最大后验概率的估计值,即通过对单个低时间分辨率视频重建来得到高时间分辨率视频,从而有效解决由于相机曝光时间过长所造成的“运动模糊”和相机帧率不足引起的“运动混叠”现象。通过理论分析与实验,证明了所提方法的有效性。

Abstract:

Any video camera equipment has certain temporal resolution, so it will cause motion blur and motion aliasing in captured video sequence. Spatial deblurring and temporal interpolation are usually adopted to solve this problem, but these methods can not solve it completely in origin. A temporal super-resolution reconstruction method based on Maximum A Posterior (MAP) probability estimation for single-video was proposed in this paper. The conditional probability model was determined in this method by reconstruction constraint, and then prior information model was established by combining temporal self-similarity in video itself. From these two models, estimation of maximum posteriori was obtained, namely reconstructed a high temporal resolution video through a single low temporal resolution video, so as to effectively remove motion blur for too long exposure time and motion aliasing for inadequate camera frame-rate. Through theoretical analysis and experiments, the validity of the proposed method is proved to be effective and efficient.

中图分类号:

郭黎廖宇陈为龙廖红华李军向军. 基于最大后验概率的单视频时间超分辨率重建算法[J]. 计算机应用, 2014, 34(12): 3580-3584.

GUO Li LIAO Yu CHEN Weilong LIAO Honghua LI Jun XIANG Jun. Single video temporal super-resolution reconstruction algorithm based on maximum a posterior[J]. Journal of Computer Applications, 2014, 34(12): 3580-3584.

参考文献

［1］ZHANG Y, ZHAO D, MA S, et al. A motion-aligned auto-regressive model for frame rate upconversion［J］. IEEE Transactions on Image Processing, 2010,19(5):1248-1258.
［2］ZHANG Y, ZHAO D, MA S, et al. A spatial-temporal auto regressive model for frame rate upconversion［J］. IEEE Transactions on Circuits and Systems for Video Technology, 2009, 19(9):1289-1301.
［3］YANG S-H, YANG C-C. Fast frame rate upconversion based on multiple frames［C］// Proceedings of the 2011 IEEE International Conference on Multimedia and Expo. Piscataway: IEEE, 2011:1-4.
［4］WU H, LIU G. A novel method for frame rate up-conversion［C］// Proceedings of the 2011 IEEE International Conference on Image Analysis and Signal Processing. Piscataway: IEEE, 2011: 6-9.
［5］SHECHTMAN E, CASPI Y, IRANI M. Space-time super-resolution［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(6): 531-544
［6］SHECHTMAN E, CASPI Y, IRANI M. Increasing space-time resolution in video［C］// Proceedings of the 7th European Conference on Computer Vision. Berlin: Springer, 2002:753-768.
［7］CHOI B T, LEE S H, KO S J. New frame rate up-conversion using bi-directional motion estimation ［J］. IEEE Transactions on Consumer Electronics, 2000, 46(3):603-609.
［8］KANG S-J, YOO D-G, SUN, LEE S-K, et al. Multiframe-based bilateral motion estimation with emphasis on stationary caption processing for frame rate up-conversion［J］. IEEE Transactions on Consumer Electronics, 2008, 54(4):1830-1838.
［9］AKIN A, CETIN M, OZCAN Z, et al. An adaptive bilateral motion estimation algorithm and its hardware architecture［J］. IEEE Transactions on Consumer Electronics, 2012, 58(2):712-720.
［10］LIM H, KIM D Y, PARK H W, et al. Motion estimation with adaptive block size for motion-compensated frame interpolation［C］// Proceedings of the 2012 IEEE International Conference on Picture Coding Symposium. Piscataway: IEEE, 2012:325-328.
［11］HUANG A M, NGUYEN T. Correlation-based motion vector processing with adaptive interpolation scheme for motion-compensated frame interpolation［J］. IEEE Transactions on Image Processing, 2009, 18(4): 740-752.
［12］YOO D-G, KANG S-J, LEE S-K, et al. Motion vector smoothing for motion-compensated frame rate upconversion［C］// Proceedings of the 2010 IEEE International SoC Design Conference. Piscataway: IEEE, 2010: 358-359.
［13］VINH T Q, KIM Y C, HONG S H. Frame rate up-conversion using forward-backward jointing motion estimation and spatio-temporal motion vector smoothing［C］// Proceedings of the 2009 IEEE International Conference on Computer Engineering and Systems. Piscataway: IEEE, 2009: 605-609.
［14］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.
［15］AGRAWAL A, GUPTA M. VEERARAGHAVAN A. Optimal coded sampling for temporal super-resolution ［C］// Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2010: 599-606.
［16］FERGUS R, SINGH B, HERTZMANN A, et al. Removing camera shake from a single photograph ［J］. ACM Transactions on Graphics, 2006, 25: 787-794.
［17］SHAN Q, JIA J, AGARWALA A. High-quality motion deblurring from a single image［J］. ACM Transactions on Graphics, 2008, 27(3):1-10.
［18］LEE S. H, KWON O. Weighted-adaptive motion compensated frame rate up-conversion［J］. IEEE Transactions on Consumer Electronics, 2003, 49(3): 485-495.