Abstract
As the Internet of Things thrives, monitors and cameras produce tons of image data every day. To efficiently process these images, many compressed imaging frameworks are proposed. A compressed imaging framework comprises two parts, image signal measurement and reconstruction. Although a plethora of measurement devices have been designed, the development of the reconstruction is relatively lagging behind. Nowadays, most of existing reconstruction algorithms in compressed imaging are optimization problem solvers based on specific priors. The computation burdens of these optimization algorithms are enormous and the solutions are usually local optimums. Meanwhile, it is inconvenient to deploy these algorithms on cloud, which hinders the popularization of compressed imaging. In this article, we dive deep into the random projection to build reconstruction algorithms for compressed imaging. We first fully utilize the information in the measurement procedure and propose a combinatorial sparse random projection (SRP) reconstruction algorithm. Then, we generalize the SRP to a novel distributed algorithm called Cloud-SRP (CSRP), which enables efficient reconstruction on cloud. Moreover, we explore the combination of SRP with conventional optimization reconstruction algorithms and propose the Iterative-SRP (ISRP), which converges to a guaranteed fixed point. With minor modifications on the naive optimization algorithms, the ISRP yields better reconstructions. Experiments on real ghost imaging reconstruction reveal that our algorithms are effective. And simulation experiments show their advantages over the classical algorithms.
- A. Beck and M. Teboulle. 2009. A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J. Imag. Sci. 2 (1 2009), 183–202.Google Scholar
Digital Library
- E. Candès, L. Demanet, D. Donoho, and L. Ying. 2006. Fast discrete curvelet transforms. SIAM J. Multisc. Model. Simul. 5 (9 2006), 861–899.Google Scholar
Cross Ref
- E. J. Candès, J. Romberg, and T. Tao. 2006. Robust uncertainty principles: Exact signal frequency information. IEEE Trans. Inf. Theor. 52 (3 2006), 489–509.Google Scholar
Digital Library
- S. H. Chan, X. Wang, and O. A. Elgendy. 2017. Plug-and-play ADMM for image restoration: Fixed-point convergence and applications. IEEE Trans. Comput. Imag. 3, 1 (3 2017), 84–98. Google Scholar
Cross Ref
- L.-H. Chang and J.-Y. Wu. 2014. An improved RIP-based performance guarantee for sparse signal reconstruction via subspace pursuit. In Proceedings of the IEEE Sensor Array and Multichannel Signal Processing Workshop. 405–408. Google Scholar
Cross Ref
- D. Donoho and A. Montanari. 2009. Message passing algorithms for compressed sensing. Proc. Nat. Acad. Sci. United States Amer. 106, 45 (11 2009), 18914–18919.Google Scholar
Cross Ref
- M. Duarte, M. A. Davenport, D. Takhar, J. N. Laska, T. Sun, K. Kelly, and R. Baraniuk. 2008. Single-pixel imaging via compressive sampling. IEEE Sig. Proc. Mag. 25 (4 2008), 83–91.Google Scholar
Cross Ref
- M. F. Duarte, S. Sarvotham, D. Baron, M. B. Wakin, and R. G. Baraniuk. 2005. Distributed compressed sensing of jointly sparse signals. In Proceedings of the 39th Asilomar Conference on Signals, Systems and Computers. 1537–1541.Google Scholar
- J. Fowler and Q. Du. 2011. Reconstructions from compressive random projections of hyperspectral imagery. In Optical Remote Sensing: Advances in Signal Processing and Exploitation Techniques. Springer, 31–48.Google Scholar
- X. Han, B. Wu, Z. Shou, X.-Y. Liu, Y. Zhang, and L. Kong. 2020. Tensor FISTA-net for real-time snapshot compressive imaging. In Proceedings of the 34th AAAI Conference on Artificial Intelligence.Google Scholar
- K. He, X. Zhang, S. Ren, and J. Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 770–778.Google Scholar
- X. Hu, S. Zhang, Z. Lu, W. Wang, and J. Xiong. 2016. Receiver disposition optimization in distributed passive radar imaging. In Proceedings of the IEEE International Geoscience and Remote Sensing Symposium. 1018–1021. Google Scholar
- S. Jalali and X. Yuan. 2019. Snapshot compressed sensing: Performance bounds and algorithms. IEEE Trans. Inf. Theor. 65, 12 (2019), 8005–8024.Google Scholar
Digital Library
- J. Ke, P. Shankar, and M. A. Neifeld. 2009. Distributed imaging using an array of compressive cameras. Optics Commun. 282, 2 (2009), 185–197. Google Scholar
Cross Ref
- L. Kong, D. Zhang, Z. He, Q. Xiang, J. Wan, and M. Tao. 2016. Embracing big data with compressive sensing: A green approach in industrial wireless networks. IEEE Commun. Mag. 54 (10 2016), 53–59.Google Scholar
Digital Library
- G. Kutyniok, W.-Q. Lim, and R. Reisenhofer. 2016. ShearLab 3D: Faithful digital shearlet transforms based on compactly supported shearlets. ACM Trans. Math. Softw. 42 (1 2016), 5:1–5:42.Google Scholar
Digital Library
- Y.-B. Lee, L. Jeonghyeon, S. Tak, K. Lee, D. Na, S. Seo, Y. Jeong, and J. C. Ye. 2016. Sparse SPM: Sparse-dictionary learning for resting-state functional connectivity MRI analysis. NeuroImage 125 (1 2016), 1032–1045.Google Scholar
Cross Ref
- P. Li and C.-H. Zhang. 2014. Compressed sensing with very sparse Gaussian random projections. arXiv:stat.ME/1408.2504.Google Scholar
- Y. Li, B. Song, R. Cao, Y. Zhang, and H. Qin. 2016. Image encryption based on compressive sensing and scrambled index for secure multimedia transmission. Trans. Multimedia Comput. Commun. Applic. 12, 4s (9 2016). Google Scholar
- X. Liu, J. Shi, X. Wu, and G. Zeng. 2018. Fast first-photon ghost imaging. Sci. Rep. 8 (3 2018), 5012:1–5012:8.Google Scholar
- X. Liu, D. Zhai, R. Chen, X. Ji, D. Zhao, and W. Gao. 2019. Depth restoration from RGB-D data via joint adaptive regularization and thresholding on manifolds. IEEE Trans. Image Proc. 28, 3 (2019), 1068–1079.Google Scholar
- X. Liu, Y. Zhu, L. Kong, C. Liu, Y. Gu, A. V. Vasilakos, and M. Wu. 2015. CDC: Compressive data collection for wireless sensor networks. IEEE Trans. Parallel Distrib. Syst. 26, 8 (2015), 2188–2197.Google Scholar
Cross Ref
- P. Llull, X. Liao, X. Yuan, J. Yang, D. Kittle, L. Carin, G. Sapiro, and D. J. Brady. 2013. Coded aperture compressive temporal imaging. Optics Express 21, 9 (2013), 10526–10545.Google Scholar
Cross Ref
- A. M. M. Mostapha, G. Alsharahi, and A. Driouach. 2018. 2D FDTD simulation of ground penetrating radar imaging under subsurface with two different antenna types. Procedia Manuf. 22 (2018), 420–427.Google Scholar
Cross Ref
- H. Palangi, R. Ward, and L. Deng. 2016. Distributed compressive sensing: A deep learning approach. IEEE Trans. Sig. Proc. 64, 17 (9 2016), 4504–4518.Google Scholar
Cross Ref
- Y. C. Pati, R. Rezaiifar, and P. S. Krishnaprasad. 1993. Orthogonal matching pursuit: Recursive function approximation with applications to wavelet decomposition. In Proceedings of the Asilomar Conference on Signals, Systems & Computers 1 (1993), 40–44.Google Scholar
- M. Rani, S. B. Dhok, and R. B. Deshmukh. 2018. A systematic review of compressive sensing: Concepts, implementations and applications. IEEE Access 6 (1 2018), 4875–4894.Google Scholar
Cross Ref
- M. A. T. Figueiredo, J. B. Dias, J. P. Oliveira, and R. D. Nowak. 2006. On total variation denoising: A new majorization-minimization algorithm and an experimental comparison with wavelet denoising. In Proceedings of the International Conference on Image Processing. 2633–2636. Google Scholar
- D. S. Taubman and M. Marcellin. 2002. JPEG2000: Image Compression Fundamentals, Standards and Practice. Vol. 11. Springer, Cham. Google Scholar
- P. Wang, J. Wang, Y. Chen, and G. Ni. 2013. Rapid processing of remote sensing images based on cloud computing. Fut. Gen. Comput. Syst. 29 (10 2013), 1963–1968.Google Scholar
Digital Library
- P. Yang, L. Kong, G. Chen, J. Shi, and G. Zeng. 2019. Cloud based sparse random projection for compressed imaging. In Proceedings of the IEEE International Conference on Smart Cloud (SmartCloud’19). 193–198.Google Scholar
- P. Yang, L. Kong, X. Liu, X. Yuan, and G. Chen. 2020. Shearlet enhanced snapshot compressive imaging. IEEE Trans. Image Proc. 29 (2020), 6466–6481.Google Scholar
Digital Library
- A. P. Yazdanpanah and E. Regentova. 2017. Compressed sensing MRI using curvelet sparsity and nonlocal total variation: CS-NLTV. Electron. Imag. 2017 (1 2017), 5–9.Google Scholar
Cross Ref
- X. Yuan. 2016. Generalized alternating projection based total variation minimization for compressive sensing. In Proceedings of the IEEE International Conference on Image Processing (ICIP’16). 2539–2543.Google Scholar
Cross Ref
- X. Yuan, Y. Liu, J. Suo, and Q. Dai. 2020. Plug-and-play algorithms for large-scale snapshot compressive imaging. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Google Scholar
- K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang. 2017. Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising. IEEE Trans. Image Proc. 26, 7 (7 2017), 3142–3155. Google Scholar
Digital Library
- K. Zhang, W. Zuo, and L. Zhang. 2018. FFDNet: Toward a fast and flexible solution for CNN based image denoising. IEEE Trans. Image Proc. 27, 9 (9 2018), 4608–4622.Google Scholar
Cross Ref
- S. Zhang and J. Xin. 2018. Minimization of transformed \(\) penalty: Theory, difference of convex function algorithm, and robust application in compressed sensing. Math. Progr. 169, 1 (5 2018), 307–336. Google Scholar
Digital Library
- M. Zhussip, S. Soltanayev, and S. Y. Chun. 2019. Training deep learning based image denoisers from undersampled measurements without ground truth and without image prior. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Google Scholar
Index Terms
Compressed Imaging Reconstruction with Sparse Random Projection
Recommendations
High Throughput MR Image Reconstruction Using Compressed Sensing
ICVGIP '14: Proceedings of the 2014 Indian Conference on Computer Vision Graphics and Image ProcessingMagnetic resonance imaging (MRI) is an essential soft tissue imaging technique. Major limitation of this imaging technique is due to its slow acquisition. MR image reconstruction using the compressed sensing (CS) has mainly two research areas, one, how ...
Generalized Feldkamp Image Reconstruction from Equiangular Cone-Beam Projection Data
CBMS '00: Proceedings of the 13th IEEE Symposium on Computer-Based Medical Systems (CBMS'00)The cone-beam approach for image reconstruction attracts an increasing attention in various applications, especially medical imaging. Previously, the traditional practical cone-beam reconstruction method, the Feldkamp algorithm, was generalized into the ...
Compressed Multi-view Imaging with Joint Reconstruction
DCC '11: Proceedings of the 2011 Data Compression ConferenceThe newly emerging sampling methodology of compressed sensing opens a door to obtain compressed data directly. How to efficiently reconstruct the original from the compressed data becomes a new challenge problem. Many reconstruction works have been ...






Comments