Video compressive sensing reconstruction via long-short-term double-pattern prediction

Abstract

The compressive sensing technology has a great potential in high-dimensional vision processing. The existing video reconstruction methods utilize the multihypothesis prediction to derive the residual sparse model from key frames. However, these methods cannot fully utilize the temporal correlation among multiple frames. Therefore, this paper proposes the video compressive sensing reconstruction via long-short-term double-pattern prediction, which consists of four main phases: the first phase reconstructs each frame independently; the second phase adaptively updates multiple reference frames; the third phase selects the hypothesis matching patches from current reference frames; the fourth phase obtains the reconstruction results by using the patches to build the residual sparse model. The experimental results demonstrate that as compared with the state-of-the-art methods, the proposed methods can obtain better prediction accuracy and reconstruction quality for video compressive sensing.

References

[1] DonohoD L. IEEE Transactions on Information Theory, 2006, 52: 1289

[2] ZhaoY, LiuZ, WangY, WuH, DingS. Entropy, 2017, 19: 599

[3] Prades N. J., Ma Y. and Huang T., Distributed Video Coding Using Compressive Sampling, IEEE Picture Coding Symposium, 1 (2009).

[4] Lu G., Block Compressed Sensing Of Natural Images, 15th International Conference on Digital Signal Processing, Cardiff, 403 (2007).

[5] FowlerJ E, MunS, TramelE W. Foundation Trends Signal Processing, 2012, 4: 297

[6] Sankaranarayanan A. C., Studer C. and Baraniuk R. G., CS-MUVI: Video Compressive Sensing for Spatial-Multiplexing Cameras, IEEE International Conference on Computational Photography, 1 (2012).

[7] Park J. Y. and Wakin M. B., A Multiscale Framework for Compressive Sensing of Video, IEEE Picture Coding Symposium, 1 (2009).

[8] SongY, YangG, XieH, ZhangD, SunX. Multimedia Tools and Applications, 2017, 76: 10083

[9] YangJ, YuanX, LiaoX. IEEE Transactions on Image Processing, 2014, 23: 4863

[10] VaswaniN. IEEE Transactions on Signal Processing, 2010, 58: 4108

[11] JungH, SungK, NayakK S, KimE Y, YeJ C. Magnetic resonance in medicine, 2009, 61: 103

[12] Tramel E. W. and Fowler J. E., Video Compressed Sensing with Multihypothesis, IEEE Data Compression Conference, 193 (2011).

[13] Chen C., Tramel E. W. and Fowler J. E., Compressed-Sensing Recovery of Images and Video Using Multihypothesis Predictions, 45th Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA, 1193 (2011).

[14] KuoY, WuK, ChenJ. Multidimensional Systems and Signal Processing, 2017, 28: 129

[15] ChenJ, ChenY Z, DongQ, KuoY H. Multimedia Tools and Application, 2015, 74: 2085

[16] Zhao C., Ma S. W. and Gao W., Image Compressive-Sensing Recovery Using Structured Laplacian Sparsity in DCT Domain and Multi-Hypothesis Prediction, IEEE International Conference on Multimedia & Expo, 1 (2014).

[17] ChenJ, XueF, KuoY H. Multimedia Tools and Applications, 2018, 74: 14873

[18] AzghaniM, KarimiM, MarvastiF. IEEE Transactions on Circuits and Systems for Video Technology, 2016, 26: 627

[19] ZhaoC, MaS W, ZhangJ. IEEE Transactions on Circuits and Systems for Video Technology, 2017, 27: 1182

[20] Zheng S., Zhang X. P., Chen J. and Kuo Y. H., A New Compressed Sensing Based Terminal-to-Cloud Video Transmission System, IEEE International Symposium on Circuits and Systems (ISCAS), Sapporo, 1 (2019).