《计算机应用研究》|Application Research of Computers

保留边缘与细节的压缩采样视频复原算法

Compressive sampling video restore algorithm with edge and detail preserving

免费全文下载 (已被下载 次)  
获取PDF全文
作者 郭宏刚,杨芳
机构 1.河北师范大学 计算机网络中心,石家庄 050024;2.河北公安警察职业学院 警务科研处,石家庄 050091
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2017)09-2871-06
DOI 10.3969/j.issn.1001-3695.2017.09.068
摘要 已有的压缩感知视频复原算法因过平滑效应难以保留视频帧的边缘与细节信息,对此提出一种基于混合稀疏性测量的压缩采样视频复原算法。编码端将视频序列分为关键帧与非关键帧,并使用相同的感知矩阵对帧的每块进行采样。解码端则设计了考虑局部稀疏性与全局稀疏性的混合稀疏性测量方案,并将其作为压缩感知视频复原问题的正则项;然后通过分裂Bregman迭代算法对关键帧进行解码,并考虑视频帧间的时间相关性对非关键帧进行细化处理。基于多组仿真实验的结果表明,本算法获得了较好的视频复原精度,并具有理想的计算时间性能。
关键词 压缩感知;虚拟现实;视频复原;稀疏性测量;稀疏编码;字典学习;视频帧重建
基金项目 河北省科技计划资助项目(15457659D,152176251)
河北省教育厅资助项目(QN2014167)
本文URL http://www.arocmag.com/article/01-2017-09-068.html
英文标题 Compressive sampling video restore algorithm with edge and detail preserving
作者英文名 Guo Honggang, Yang Fang
机构英文名 1.ComputerNetworkCenter,HebeiNormalUniversity,Shijiazhuang050024,China;2.Dept.ofPoliceScientificResearch,HebeiPublicSecurityPoliceVocationalCollege,Shijiazhuang050091,China
英文摘要 The existing restore algorithms of compressive sensing video are difficult to preserve the side and detail information of video frames due to the over-smoothing effect, this paper proposed a hybrid sparsity measurement based restore algorithm for compressive sampling video to solve that problem. In the encoding phase, it divided video sequence into key frames and non-key frames, and used the same sensing matrix to sample each patches of the frame. In the decoding phase, it designed a hybrid sparsity measurement schema considering local sparsity and global sparsity, and replaced the regularization term by the proposed hybrid sparsity measurement. Then, it decoded the key frames by split Bregman iteration algorithm, and refined the non-key frames by considering video inter-frame temporal correlation. Several simulation experimental results show that the proposed algorithm realizes better video restore accuracy, at the same time it shows a ideal computational complexity perfor-mance.
英文关键词 compressive sensing; virtual reality; video restore; sparsity measure; sparse coding; dictionary learning; video frame reconstruction
参考文献 查看稿件参考文献
  [1] 戴琼海, 付长军, 季向阳. 压缩感知研究[J] . 计算机学报, 2011, 34(3):425-434.
[2] Kose K, Gunay O, Cetin A E. Compressive sensing using the modified entropy functional[J] . Digital Signal Processing, 2014, 24(1):63-70.
[3] 刘鲁锋, 杜新鹏, 成礼智. 一种基于粒子群优化的稀疏恢复算法[J] . 电子与信息学报, 2013, 35(11):2733-2738.
[4] 韩学兵, 张颢. 模型噪声中的稀疏恢复算法研究[J] . 电子与信息学报, 2012, 34(8):1813-1818.
[5] 杜海顺, 张旭东, 金勇, 等. 基于Gabor低秩恢复稀疏表示分类的人脸图像识别方法[J] . 电子学报, 2014, 42(12):2386-2393.
[6] 叶培新, 魏秀杰. 通过正交多匹配追踪恢复稀疏信号(英文)[J] . 南开大学学报:自然科学版, 2015(5):65-71.
[7] Wang Jungang, Wei Ting, Zhou Yubin. Optimal error bound and simplified Tikhonov regularization method for a backward problem for the time-fractional diffusion equation[J] . Journal of Computational & Applied Mathematics, 2015, 279(4):277-292.
[8] Savage J, Chen Ke. On multigrids for solving a class of improved total variation based staircasing reduction models[M] // Image Processing Based on Partial Differential Equations. Berlin:Springer, 2007:69-94.
[9] 任福全, 邱天爽. 基于空—时加权全变差正则项的视频复原算法[J] . 电子与信息学报, 2013, 35(4):820-825.
[10] 胡学刚, 吴勇, 刘艳. 一种变步长迭代正则化图像复原的新算法[J] . 计算机应用研究, 2010, 27(4):1572-1574, 1597.
[11] Park J Y, Wakin M B. A multiscale framework for compressive sen-sing of video[C] //Proc of Conference on Picture Coding Symposium. [S. l. ] :IEEE Press, 2009:1-4.
[12] Ma Jianwei, Plonka G, Hussaini M Y. Compressive video sampling with approximate message passing decoding[J] . IEEE Trans on Circuits & Systems for Video Technology, 2012, 22(9):1354-1364.
[13] Yang Jianbo, Yuan Xin, Liao Xuejun, et al. Video compressive sensing using Gaussian mixture models[J] . IEEE Trans on Image Processing, 2014, 23(11):4863-4878.
[14] Dabov K, Foi A, Katkovnik V, et al. Image denoising by sparse 3-D transform-domain collaborative filtering[J] . IEEE Trans on Image Processing, 2007, 16(8):2080-2095.
[15] Zhang Jian, Zhao Chen, Zhao Debin, et al. Image compressive sen-sing recovery using adaptively learned sparsifying basis via L0 minimization[J] . Signal Processing, 2014, 103(10):114-126.
[16] Zhang Jian, Zhao Debin, Zhao Chen, et al. Image compressive sensing recovery via collaborative sparsity[J] . IEEE Journal on Emerging & Selected Topics in Circuits & Systems, 2012, 2(3):287-296.
[17] Chen Chen, Tramel E W, Fowler J E. Compressed-sensing recovery of images and video using multihypothesis predictions[C] // Proc of Conference on Circuits, Systems & Computers. 2011:1193-1198.
[18] Smith L N, Elad M. Improving dictionary learning:multiple dictionary updates and coefficient reuse[J] . IEEE Signal Processing Letters, 2013, 20(1):79-82.
[19] Aharon M, Elad M, Bruckstein A K. K-SVD:an algorithm for designing overcomplete dictionaries for sparse representation[J] . IEEE Trans on Signal Processing, 2015, 54(11):4311-4322.
[20] Tropp J, Gilbert A C. Signal recovery from random measurements via orthogonal matching pursuit[J] . IEEE Trans on Information Theory, 2007, 53(12):4655-4666.
[21] Zhang Jian, Zhao Debin, Zhao Chen, et al. Compressed sensing recovery via collaborative sparsity[C] //Proc of Data Compression Conference. 2012:287-296.
[22] Eslahi N, Aghagolzadeh A, Andargoli S M H. Recovery of compressive video sensing via dictionary learning and forward prediction[C] //Proc of International Symposium on Telecommunications. 2014:833-838.
[23] Yin Baocai, Shi Yunhui, Ding Wenpeng, et al. Compressive sampling and sparse reconstruction of images/videos[J] . Scientia Sinica, 2013, 43(2):226-242.
[24] Hosseini M S, Plataniotis K N. High-accuracy total variation with application to compressed video sensing[J] . IEEE Trans on Image Processing, 2014, 23(9):3869-3884.
收稿日期 2016/6/13
修回日期 2016/7/27
页码 2871-2876
中图分类号 TP391.41;TP301.6
文献标志码 A