Signal Recovery and System Calibration from Multiple Compressive Poisson Measurements
Abstract
The measurement matrix employed in compressive sensing typically cannot be known precisely a priori and must be estimated via calibration. One may take multiple compressive measurements, from which the measurement matrix and underlying signals may be estimated jointly. This is of interest as well when the measurement matrix may change as a function of the details of what is measured. This problem has been considered recently for Gaussian measurement noise, and here we develop this idea with application to Poisson systems. A collaborative maximum likelihood algorithm and alternating proximal gradient algorithm are proposed, and associated theoretical performance guarantees are established based on newly derived concentration-of-measure results. A Bayesian model is then introduced, to improve flexibility and generality. Connections between the maximum likelihood methods and the Bayesian model are developed, and example results are presented for a real compressive X-ray imaging system.
- Authors:
-
- Duke Univ., Durham, NC (United States)
- Ecole Polytechnique Federale Lausanne (Switzlerland)
- Univ. College London (United Kingdom)
- Publication Date:
- Research Org.:
- Univ. of Michigan, Ann Arbor, MI (United States)
- Sponsoring Org.:
- USDOE National Nuclear Security Administration (NNSA), Office of Nonproliferation and Verification Research and Development (NA-22)
- OSTI Identifier:
- 1367084
- Grant/Contract Number:
- NA0002534
- Resource Type:
- Accepted Manuscript
- Journal Name:
- SIAM Journal on Imaging Sciences
- Additional Journal Information:
- Journal Volume: 8; Journal Issue: 3; Journal ID: ISSN 1936-4954
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 47 OTHER INSTRUMENTATION; compressive sensing; Poisson compressive sensing; system calibration; concentration-of-measure; Bayesian compressive sensing; X-ray imaging
Citation Formats
Wang, Liming, Huang, Jiaji, Yuan, Xin, Krishnamurthy, Kalyani, Greenberg, Joel, Cevher, Volkan, Rodrigues, Miguel R. D., Brady, David, Calderbank, Robert, and Carin, Lawrence. Signal Recovery and System Calibration from Multiple Compressive Poisson Measurements. United States: N. p., 2015.
Web. doi:10.1137/140998779.
Wang, Liming, Huang, Jiaji, Yuan, Xin, Krishnamurthy, Kalyani, Greenberg, Joel, Cevher, Volkan, Rodrigues, Miguel R. D., Brady, David, Calderbank, Robert, & Carin, Lawrence. Signal Recovery and System Calibration from Multiple Compressive Poisson Measurements. United States. https://doi.org/10.1137/140998779
Wang, Liming, Huang, Jiaji, Yuan, Xin, Krishnamurthy, Kalyani, Greenberg, Joel, Cevher, Volkan, Rodrigues, Miguel R. D., Brady, David, Calderbank, Robert, and Carin, Lawrence. Thu .
"Signal Recovery and System Calibration from Multiple Compressive Poisson Measurements". United States. https://doi.org/10.1137/140998779. https://www.osti.gov/servlets/purl/1367084.
@article{osti_1367084,
title = {Signal Recovery and System Calibration from Multiple Compressive Poisson Measurements},
author = {Wang, Liming and Huang, Jiaji and Yuan, Xin and Krishnamurthy, Kalyani and Greenberg, Joel and Cevher, Volkan and Rodrigues, Miguel R. D. and Brady, David and Calderbank, Robert and Carin, Lawrence},
abstractNote = {The measurement matrix employed in compressive sensing typically cannot be known precisely a priori and must be estimated via calibration. One may take multiple compressive measurements, from which the measurement matrix and underlying signals may be estimated jointly. This is of interest as well when the measurement matrix may change as a function of the details of what is measured. This problem has been considered recently for Gaussian measurement noise, and here we develop this idea with application to Poisson systems. A collaborative maximum likelihood algorithm and alternating proximal gradient algorithm are proposed, and associated theoretical performance guarantees are established based on newly derived concentration-of-measure results. A Bayesian model is then introduced, to improve flexibility and generality. Connections between the maximum likelihood methods and the Bayesian model are developed, and example results are presented for a real compressive X-ray imaging system.},
doi = {10.1137/140998779},
journal = {SIAM Journal on Imaging Sciences},
number = 3,
volume = 8,
place = {United States},
year = {Thu Sep 17 00:00:00 EDT 2015},
month = {Thu Sep 17 00:00:00 EDT 2015}
}
Web of Science
Works referenced in this record:
An Introduction To Compressive Sampling
journal, March 2008
- Candes, E. J.; Wakin, M. B.
- IEEE Signal Processing Magazine, Vol. 25, Issue 2
Signal Processing With Compressive Measurements
journal, April 2010
- Davenport, M. A.; Boufounos, P. T.; Wakin, M. B.
- IEEE Journal of Selected Topics in Signal Processing, Vol. 4, Issue 2
Single-pixel imaging via compressive sampling
journal, March 2008
- Duarte, Marco F.; Davenport, Mark A.; Takhar, Dharmpal
- IEEE Signal Processing Magazine, Vol. 25, Issue 2, p. 83-91
Bayesian latent variable models for mixed discrete outcomes
journal, December 2004
- Dunson, D. B.; Herring, A. H.
- Biostatistics, Vol. 6, Issue 1
The restricted isometry property for random block diagonal matrices
journal, January 2015
- Eftekhari, Armin; Yap, Han Lun; Rozell, Christopher J.
- Applied and Computational Harmonic Analysis, Vol. 38, Issue 1
Snapshot molecular imaging using coded energy-sensitive detection
journal, January 2013
- Greenberg, Joel A.; Krishnamurthy, Kalyani; Brady, David
- Optics Express, Vol. 21, Issue 21
This is SPIRAL-TAP: Sparse Poisson Intensity Reconstruction ALgorithms—Theory and Practice
journal, March 2012
- Harmany, Z. T.; Marcia, R. F.; Willett, R. M.
- IEEE Transactions on Image Processing, Vol. 21, Issue 3
General Deviants: An Analysis of Perturbations in Compressed Sensing
journal, April 2010
- Herman, M. A.; Strohmer, T.
- IEEE Journal of Selected Topics in Signal Processing, Vol. 4, Issue 2
Multiframe image estimation for coded aperture snapshot spectral imagers
journal, January 2010
- Kittle, David; Choi, Kerkil; Wagadarikar, Ashwin
- Applied Optics, Vol. 49, Issue 36
Concentration inequalities for dependent random variables via the martingale method
journal, November 2008
- Kontorovich, Leonid (Aryeh); Ramanan, Kavita
- The Annals of Probability, Vol. 36, Issue 6
Coded aperture compressive temporal imaging
journal, January 2013
- Llull, Patrick; Liao, Xuejun; Yuan, Xin
- Optics Express, Vol. 21, Issue 9, p. 10526-10545
Snapshot 2D tomography via coded aperture x-ray scatter imaging
journal, January 2013
- MacCabe, Kenneth P.; Holmgren, Andrew D.; Tornai, Martin P.
- Applied Optics, Vol. 52, Issue 19
Concentration of Measure for Block Diagonal Matrices With Applications to Compressive Signal Processing
journal, December 2011
- Park, Jae Young; Yap, Han Lun; Rozell, Christopher J.
- IEEE Transactions on Signal Processing, Vol. 59, Issue 12
Performance Bounds for Expander-Based Compressed Sensing in Poisson Noise
journal, September 2011
- Raginsky, Maxim; Jafarpour, Sina; Harmany, Zachary T.
- IEEE Transactions on Signal Processing, Vol. 59, Issue 9
Concentration of Measure Inequalities in Information Theory, Communications, and Coding
journal, January 2013
- Raginsky, Maxim
- Foundations and Trends® in Communications and Information Theory, Vol. 10, Issue 1-2
Compressed Sensing Performance Bounds Under Poisson Noise
journal, August 2010
- Raginsky, Maxim; Willett, Rebecca M.; Harmany, Zachary T.
- IEEE Transactions on Signal Processing, Vol. 58, Issue 8
Nonlinear total variation based noise removal algorithms
journal, November 1992
- Rudin, Leonid I.; Osher, Stanley; Fatemi, Emad
- Physica D: Nonlinear Phenomena, Vol. 60, Issue 1-4
A Bregman Matrix and the Gradient of Mutual Information for Vector Poisson and Gaussian Channels
journal, May 2014
- Wang, Liming; Carlson, David Edwin; Rodrigues, Miguel R. D.
- IEEE Transactions on Information Theory, Vol. 60, Issue 5, p. 2611-2629
Photon level chemical classification using digital compressive detection
journal, November 2012
- Wilcox, David S.; Buzzard, Gregery T.; Lucier, Bradley J.
- Analytica Chimica Acta, Vol. 755
Multiscale Poisson Intensity and Density Estimation
journal, September 2007
- Willett, Rebecca M.; Nowak, Robert D.
- IEEE Transactions on Information Theory, Vol. 53, Issue 9
Robustly Stable Signal Recovery in Compressed Sensing With Structured Matrix Perturbation
journal, September 2012
- Yang, Zai; Zhang, Cishen; Xie, Lihua
- IEEE Transactions on Signal Processing, Vol. 60, Issue 9
Negative Binomial Process Count and Mixture Modeling
journal, February 2015
- Zhou, Mingyuan; Carin, Lawrence
- IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 37, Issue 2
Sparsity-Cognizant Total Least-Squares for Perturbed Compressive Sampling
journal, May 2011
- Zhu, Hao; Leus, Geert; Giannakis, Georgios B.
- IEEE Transactions on Signal Processing, Vol. 59, Issue 5
Works referencing / citing this record:
Compressive video sensing with side information
journal, January 2017
- Yuan, Xin; Sun, Yangyang; Pang, Shuo
- Applied Optics, Vol. 56, Issue 10