Abstract
In recent years, block-based compressive sensing (BCS) has been extensively studied because it can reduce computational complexity and data storage by dividing the image into smaller patches, but the performance of the reconstruction algorithm is not satisfactory. In this paper, a new reconstruction model for image and video is proposed. The model makes full use of spatio-temporal correlation and utilizes low-rank tensor approximation to improve the quality of the reconstructed image and video. For image recovery, the proposed model obtains a low-rank approximation of a tensor formed by non-local similar patches, and improves the reconstruction quality from a spatial perspective by combining non-local similarity and low-rank property. For video recovery, the reconstruction process is divided into two phases. In the first phase, each frame of the video sequence is regarded as an independent image to be reconstructed by taking advantage of spatial property. The second phase performs tensor approximation through searching similar patches within frames near the target frame, to achieve reconstruction by putting the spatio-temporal correlation into full play. The resulting model is solved by an efficient Alternating Direction Method of Multipliers (ADMM) algorithm. A series of experiments show that the quality of the proposed model is comparable to the current state-of-the-art recovery methods.
Similar content being viewed by others
References
Asif MS, Romberg J (2013) Fast and accurate algorithms for re-weighted ℓ1-norm minimization. IEEE Trans Signal Process 61(23):5905–5916
Baraniuk RG, Cevher V, Duarte MF, et al (2010) Model-based compressive sensing. IEEE Trans Inf Theory 56(4)1982–2001. https://doi.org/10.1109/TIT.2010.2040894
Bruckstein AM, Donoho DL, Elad M (2009) From sparse solutions of systems of equations to sparse modeling of signals and images. SIAM Rev 51(1):34–81
Candès EJ, Wakin MB, Boyd SP (2007) Enhancing sparsity by reweighted L1 minimization. J Fourier Anal Appl 14(5):877–905. https://doi.org/10.1007/s00041-008-9045-x
Candès EJ, Wakin MB, Boyd SP (2007) Enhancing sparsity by reweighted L1 minimization. J Fourier Anal Appl 14(5):877–905
Chen C, Tramel EW, Fowler JE (2012) Compressed-sensing recovery of images and video using multihypothesis predictions, in: IEEE 46th Signals, systems and computers, pp. 1193–1198.
Dong W, Shi G, Li X (2014) Compressive sensing via nonlocal low-rank regularization. IEEE Trans Image Process 23(8):3618–3632
Donoho DL (2006) Compressed sensing. IEEE Trans Inf Theory 52(4):1289–1306
Eftekhari A, Wakin MB (2015) New analysis of manifold Embeddings and signal recovery from compressive measurements. Appl Comput Harmon Anal 39(1):67–109. https://doi.org/10.1016/j.acha.2014.08.005
Emmanuel J. Candès, Wakin M B , Boyd S P, "Enhancing Sparsity by Reweighted L1 Minimization," Journal of Fourier Analysis &Applications, vol. 14, no. 5, pp. 877-905, 2007.
Fowler JE, Mun S, Tramel EW (2012) Block-based compressed sensing of images and video. Found Trends Signal Process 4(4):297–416
Gan L (2007) Block compressed sensing of natural images, in: IEEE Proceedings of the 15th International Conference on Digital Signal Processing, pp. 403–406.
Hegde C, Baraniuk RG (2012) Signal recovery on incoherent manifolds. IEEE Trans. Inf. Theory 58(12):7204–7214
Hegde C, Wakin M, Baraniuk R (2008) Random projections for manifold learning, in: Advances in neural information processing systems, pp. 641–648.
Illiasdis M, Spinoulas L, Katsaggelos AK (2018) Deep fully-connected networks for video compressive sensing, Elsevier Digital Signal Processing, 72
Kindermann S, Osher S, Jones PW (2005) Deblurring and denoising of images by nonlocal functionals. Siam Journal on Multiscale Modeling & Simulation 4(4):1091–1115. https://doi.org/10.1137/050622249
Li C, Yin W, Jiang H, Zhang Y (2013) An efficient augmented lagrangian method with applications to total variation minimization. Comput Optim Appl 56(3):507–530
Lingala SG, Hu Y, DiBella E, Jacob M (2011) Accelerated dynamic MRI exploiting sparsity and low-rank structure: k-t SLR. IEEE TransMed Imag 30(5):1042–1054
Lu H, Li S, Liu Q et al. (2018) MF-LRTC: Multi-filters guided low-rank tensor coding for image restoration, NEUROCOMPUTING.
Mairal J, Elad M, Sapiro G (2007) Sparse representation for color image restoration. IEEE Trans Image Process 17(1):53–69
Mun S, Fowler JE (2010) Block Compressed Sensing of Images Using Directional Transforms, in: IEEE 17th International Conference on Image Processing, p. 547.
Mun S, Fowler JE (2011) Residual reconstruction for block-based compressed sensing of video, in: Proc. IEEE Data Compress. Conf. (DCC), pp. 183–192.
Palangi H, Ward R, Deng L (2016) Distributed compressive sensing: a deep learning approach. IEEE Trans Signal Process 64(17):4504–4518. https://doi.org/10.1109/TSP.2016.2557301
Shi W, Jiang F, Liu S et al. (2019) Scalable convolutional neural network for image compressed sensing. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Siddamal KV, Bhat SP, Saroja VS (2015) A survey on compressive sensing, in: IEEE 2nd International Conference on Electronics and Communication Systems, pp. 639–643.
Tramel EW, Fowler JE (2011) Video compressed sensing with multihypothesis, in: Proc. IEEE Data Compress. Conf. (DCC), pp. 193–202.
Ulyanov D, Vedaldi A, Lempitsky V (2018) Deep image prior, IEEE/CVF conference on computer vision and pattern recognition (CVPR)
Van Veen D, Jalal A, Soltanolkotabi M, et al. (2018) Compressed sensing with deep image prior and learned regularization
Xu J, Ma J, Zhang D, Zhang Y, Lin S (2012) Improved total variation minimization method for compressive sensing by intra-prediction. Signal Process 92(11):2614–2623
Zhang J, Ghanem B (2018) ISTA-Net: interpretable optimization-inspired deep network for image compressive sensing. IEEE Conference on Computer Vision and Pattern Recognition:1828–1837. https://doi.org/10.1109/CVPR.2018.00196
Zhang X, Burger M, Bresson X (2010) Bregmanized nonlocal regularization for deconvolution and sparse reconstruction. SIAM J Imag Sci 3(3):253–276
Zhang J, Zhao D, Zhao C (2012) Image compressive sensing recovery via collaborative sparsity. IEEE J Emerging Sel Top Circuits Syst 2(3):380–391
Zhang J, Zhao C, Zhao D et al (2014) Image compressive sensing recovery using adaptively learned sparsifying basis via L0 minimization. Signal Process 103:114–126. https://doi.org/10.1016/j.sigpro.2013.09.025
Zhang J, Zhao C, Gao W (2020) Optimization-inspired compact deep compressive sensing. IEEE Journal of Selected Topics in Signal Processing
Zhao C, Ma S, Gao W (2014) Video compressive sensing via structured Laplacian modelling, in: Proc. IEEE Vis. Commun. Image Process. Conf. pp. 402–405.
Zhao C, Ma S, Zhang J, Xiong R (2016) Video compressive sensing reconstruction via reweighted residual sparsity. IEEE Trans Circuits Syst Video Technol 27(6):1–1
Funding
This work was supported by National Natural Science Foundation (No.61501069) and by Technology Innovation and Application Development Project of Chongqing (cstc2019jscx-msxmX0167).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zhong, Y., Zhang, J., Zhou, Z. et al. Recovery of image and video based on compressive sensing via tensor approximation and Spatio-temporal correlation. Multimed Tools Appl 80, 7433–7450 (2021). https://doi.org/10.1007/s11042-020-09907-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-09907-1