Recursive Reconstruction of Sparse Signal Sequences

Chapter
Part of the Signals and Communication Technology book series (SCT)

Abstract

In this chapter we describe our recent work on the design and analysis of recursive algorithms for causally reconstructing a time sequence of (approximately) sparse signals from a greatly reduced number of linear projection measurements. The signals are sparse in some transform domain referred to as the sparsity basis and their sparsity patterns (support set of the sparsity basis coefficients) can change with time. By “recursive", we mean using only the previous signal’s estimate and the current measurements to get the current signal’s estimate. We also briefly summarize our exact reconstruction results for the noise-free case and our error bounds and error stability results (conditions under which a time-invariant and small bound on the reconstruction error holds at all times) for the noisy case. Connections with related work are also discussed. A key example application where the above problem occurs is dynamic magnetic resonance imaging (MRI) for real-time medical applications such as interventional radiology and MRI-guided surgery, or in functional MRI to track brain activation changes. Cross-sectional images of the brain, heart, larynx or other human organ images are piecewise smooth, and thus approximately sparse in the wavelet domain. In a time sequence, their sparsity pattern changes with time, but quite slowly. The same is also often true for the nonzero signal values. This simple fact, which was first observed in our work, is the key reason that our proposed recursive algorithms can achieve provably exact or accurate reconstruction from very few measurements.

References

  1. 1.
    Wakin M, Laska J, Duarte M, Baron D, Sarvotham S, Takhar D, Kelly K, Baraniuk R (2006) An architecture for compressive imaging. In: IEEE Intl Conf Image Proc (ICIP)Google Scholar
  2. 2.
    Haupt J, Nowak R (2006) Signal reconstruction from noisy random projections. IEEE Trans Inf Theory 52(9):4036–4048Google Scholar
  3. 3.
    Candès EJ, Li X, Ma Y, Wright J (2009) Robust principal component analysis? J ACM 58(1): 1–37Google Scholar
  4. 4.
    Qiu C, Vaswani N (2011) Support predicted modified-cs for recursive robust principal components’ pursuit. In: IEEE Intl Symp Info Th (ISIT)Google Scholar
  5. 5.
    Qiu C, Vaswani N (2011) Recursive sparse recovery in large but correlated noise. Allerton Conf on Communication, Control, and, ComputingGoogle Scholar
  6. 6.
    Carron I “Nuit blanche”, in http://nuit-blanche.blogspot.com/
  7. 7.
    “Rice compressive sensing resources”, in http://www-dsp.rice.edu/cs
  8. 8.
    Candes E, Romberg J, Tao T (2006) Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information. IEEE Trans Inf Theory 52(2):489–509MathSciNetCrossRefMATHGoogle Scholar
  9. 9.
    Donoho D (2006) Compressed sensing. IEEE Trans Inf Theory 52(4):1289–1306MathSciNetCrossRefGoogle Scholar
  10. 10.
    Candes E, Tao T (2005) Decoding by linear programming. IEEE Trans Inf Theory 51(12):4203–4215MathSciNetCrossRefMATHGoogle Scholar
  11. 11.
    Gamper U, Boesiger P, Kozerke S (2008) Compressed sensing in dynamic mri. Magn Reson Med 59(2):365–373CrossRefGoogle Scholar
  12. 12.
    Wakin M, Laska J, Duarte M, Baron D, Sarvotham S, Takhar D, Kelly K, Baraniuk R (2006) Compressive imaging for video representation and coding. In: Proc April, Picture Coding Symposium (PCS), Beijing, ChinaGoogle Scholar
  13. 13.
    Jung H, Sung KH, Nayak KS, Kim EY, Ye JC (2009) k-t focuss: a general compressed sensing framework for high resolution dynamic mri. Magn Reson Med 61:103–116Google Scholar
  14. 14.
    Vaswani N (2008) Kalman filtered compressed sensing. In: IEEE Intl Conf Image Proc (ICIP)Google Scholar
  15. 15.
    Vaswani N (2010) LS-CS-residual (LS-CS): Compressive Sensing on Least Squares residual. IEEE Trans Signal Process 58(8):4108–4120MathSciNetCrossRefGoogle Scholar
  16. 16.
    Vaswani N, Lu W (2009) Modified-cs: Modifying compressive sensing for problems with partially known support. In: IEEE Intl Symp Info Th (ISIT)Google Scholar
  17. 17.
    Vaswani N, Lu W (2010) Modified-cs: Modifying compressive sensing for problems with partially known support. IEEE Trans Signal Process 58(9):4595–4607MathSciNetCrossRefGoogle Scholar
  18. 18.
    Lu W, Vaswani N (2009) Modified Compressive Sensing for Real-time Dynamic MR Imaging. In IEEE Intl Conf Image Proc (ICIP)Google Scholar
  19. 19.
    Lu W, Li T, Atkinson I, Vaswani N (2011) Modified-cs-residual for recursive reconstruction of highly undersampled functional mri sequences. In, IEEE Intl Conf Image Proc (ICIP)Google Scholar
  20. 20.
    Lu W, Vaswani N (2012) Regularized modified bpdn for noisy sparse reconstruction with partial erroneous support and signal value knowledge. IEEE Trans Signal process 60(1):182–196Google Scholar
  21. 21.
    Lu W, Vaswani N (2012) Exact reconstruction conditions for regularized modified basis pursuit. IEEE Trans Signal Process 60(5):2634–2640Google Scholar
  22. 22.
    Vaswani N (2010) Stability (over time) of Modified-CS for Recursive Causal Sparse Reconstruction. In Allerton Conf Communication, Control, and, ComputingGoogle Scholar
  23. 23.
    Mallat SG, Zhang Z (1993) Matching pursuits with time-frequency dictionaries. IEEE Trans Signal Process 41(12):3397–3415CrossRefMATHGoogle Scholar
  24. 24.
    Chen S, Donoho D, Saunders M (1998) Atomic decomposition by basis pursuit. SIAM J Sci Comput 20:33–61MathSciNetCrossRefGoogle Scholar
  25. 25.
    Wipf DP, Rao BD (2004) Sparse bayesian learning for basis selection. IEEE Trans Signal Process 52:2153–2164MathSciNetCrossRefGoogle Scholar
  26. 26.
    Tropp JA (2006) Just relax: Convex programming methods for identifying sparse signals. IEEE Trans Inf Theory 1030–1051Google Scholar
  27. 27.
    Candes E (2008) The restricted isometry property and its implications for compressed sensing. Compte Rendus de l’Academie des Sciences, Paris, Serie I:589–592MathSciNetGoogle Scholar
  28. 28.
    Candes E, Tao T (2007) The dantzig selector: statistical estimation when p is much larger than n. Ann Stat 35(6):2313–2351MathSciNetCrossRefMATHGoogle Scholar
  29. 29.
    Tropp J, Gilbert A (2007) Signal recovery from random measurements via orthogonal matching pursuit. IEEE Trans Inf Theory 53(12):4655–4666MathSciNetCrossRefGoogle Scholar
  30. 30.
    Dai W, Milenkovic O (2009) Subspace pursuit for compressive sensing signal reconstruction. IEEE Trans Inf Theory 55(5):2230–2249MathSciNetCrossRefGoogle Scholar
  31. 31.
    Needell D, Tropp JA (May 2009) Cosamp: Iterative signal recovery from incomplete and inaccurate samples. Appl Comp Harmonic Anal 26(3):301–321MathSciNetCrossRefMATHGoogle Scholar
  32. 32.
    Carmi A, Gurfil P, Kanevsky D (2010) Methods for sparse signal recovery using kalman filtering with embedded pseudo-measurement norms and quasi-norms. IEEE Trans Signal Process 2405–2409Google Scholar
  33. 33.
    Sejdinovic D, Andrieu C, Piechocki R (2010) Bayesian sequential compressed sensing in sparse dynamical systems. In Allerton Conf Communication, Control, and, ComputingGoogle Scholar
  34. 34.
    Ziniel J, Potter LC, Schniter P (2010) Tracking and smoothing of time-varying sparse signals via approximate belief propagation. Asilomar Conf Sig Sys CompGoogle Scholar
  35. 35.
    Zhang Z, Rao BD (2011) Sparse signal recovery with temporally correlated source vectors using sparse bayesian learning. IEEE J Sel Topics Sig Proc (Special Issue on Adaptive Sparse Representation of Data and Applications in Signal and Image Processing) 5(5):912–926CrossRefGoogle Scholar
  36. 36.
    Charles A, Asif MS, Romberg J, Rozell C (2011) Sparsity penalties in dynamical system estimation. In Conf Info, Sciences and SystemsGoogle Scholar
  37. 37.
    Garcia-Frias J, Esnaola I (2007) Exploiting prior knowledge in the recovery of signals from noisy random projections. In Data Comp ConfGoogle Scholar
  38. 38.
    Ji S, Xue Y, Carin L (2008) Bayesian compressive sensing. IEEE Trans Signal Process 56(6):2346–2356Google Scholar
  39. 39.
    Schniter P, Potter L, Ziniel J (2008) Fast bayesian matching pursuit: Model uncertainty and parameter estimation for sparse linear models. In: Information Theory and Applications (ITA)Google Scholar
  40. 40.
    La C, Do M (2005) “Signal reconstruction using sparse tree representations”, in SPIE Wavelets XI. San Diego, CaliforniaGoogle Scholar
  41. 41.
    Baraniuk R, Cevher V, Duarte M, Hegde C (2010) Model-based compressive sensing. IEEE Trans Inf Theory 56(4):1982–2001Google Scholar
  42. 42.
    Eldar Yonina C, Moshe Mishali (2009) Robust recovery of signals from a structured union of subspaces. IEEE Trans Inf Theory 55(11):5302–5316CrossRefGoogle Scholar
  43. 43.
    Som S, Potter LC, Schniter P (2010) Compressive imaging using approximate message passing and a markov-tree prior. In Asilomar Conf Sig Sys CompGoogle Scholar
  44. 44.
    Khajehnejad A, Xu W, Avestimehr A, Hassibi B (2009) Weighted l1 minimization for sparse recovery with prior information. In: IEEE Intl Symp Info Th (ISIT)Google Scholar
  45. 45.
    Khajehnejad A, Xu W, Avestimehr A, Hassibi B (2011) Weighted \(\ell _{1}\) minimization for sparse recovery with Nonuniform Sparse Models. IEEE Trans Signal Process 59(5):1985–2001Google Scholar
  46. 46.
    Miosso CJ, von Borries R, Argez M, Valazquez L, Quintero C, Potes C (2009) Compressive sensing reconstruction with prior information by iteratively reweighted least-squares. IEEE Trans Signal Process 57(6):2424–2431MathSciNetCrossRefGoogle Scholar
  47. 47.
    Donoho D (2006) For most large underdetermined systems of linear equations, the minimal ell-1 norm solution is also the sparsest solution. Comm Pure App Math 59(6):797–829MathSciNetCrossRefMATHGoogle Scholar
  48. 48.
    Stankovic V, Stankovic L, Cheng S (2009) Compressive image sampling with side information. In: ICIPGoogle Scholar
  49. 49.
    Carrillo R, Polania LF, Barner K (2010) Iterative algorithms for compressed sensing with patially known support. In: ICASSPGoogle Scholar
  50. 50.
    Jongmin K, Ok Kyun L, Jong Chul Y (2012) Dynamic sparse support tracking with multiple measurement vectors using compressive MUSIC. In: ICASSPGoogle Scholar
  51. 51.
    Stojnic M (2010) Block-length dependent thresholds for \(\ell _2 / \ell _1\)-optimization in block-sparse compressed sensing. In: ICASSPGoogle Scholar
  52. 52.
    Jacques L (2010) A short note on compressed sensing with partially known signal support, Signal Processing 90(12):3308–3312Google Scholar
  53. 53.
    Lu W, Vaswani N (2010) Modified bpdn for noisy compressive sensing with partially known support. In: IEEE Intl Conf Acoustics, Speech, Sig Proc (ICASSP)Google Scholar
  54. 54.
    Friedlander MP, Mansour H, Saab R, Yilmaz O (2012) Recovering compressively sampled signals using partial support information. IEEE Trans Inf Theory 58(2):1122–1134MathSciNetCrossRefGoogle Scholar
  55. 55.
    Asif MS, Romberg J (2009) Dynamic updating for sparse time varying signals In: Conf. Info, Sciences and SystemsGoogle Scholar
  56. 56.
    Yin W, Osher S, Goldfarb D, Darbon J (2008) Bregman iterative algorithms for l1-minimization with applications to compressed sensing. SIAM J Imaging Sci 1(1):143–168MathSciNetCrossRefMATHGoogle Scholar
  57. 57.
    Malioutov DM, Sanghavi S, Willsky AS (2008) Compressed sensing with sequential observations. In: IEEE Intl Conf Acoustics, Speech, Sig Proc (ICASSP)Google Scholar
  58. 58.
    Angelosante D, Giannakis GB (2009) Rls-weighted lasso for adaptive estimation of sparse signals. In: IEEE Intl Conf Acoustics, Speech, Sig Proc (ICASSP)Google Scholar
  59. 59.
    Pierre J. Garrigues and Laurent El Ghaoui (2008) An homotopy algorithm for the lasso with online observations. In: Adv Neural Info Proc Sys (NIPS)Google Scholar
  60. 60.
    Candes EJ, Wakin MB, Boyd SP (2008) Enhancing sparsity by reweighted l(1) minimization. J Fourier Anal Appl 14(5–6):877–905MathSciNetCrossRefMATHGoogle Scholar
  61. 61.
    Chartrand R, Yin W (2008) Iteratively reweighted algorithms for compressive sensing. In: IEEE Intl Conf Acoustics, Speech, Sig Proc (ICASSP)Google Scholar
  62. 62.
    Wang Y, Yin W (2010) Sparse signal reconstruction via iterative support detection. SIAM J Imaging Sci 3(3):462–491MathSciNetCrossRefMATHGoogle Scholar
  63. 63.
    Angelosante D, Giannakis GB, Grossi E (2009) Compressed sensing of time-varying signals. Dig Sig Proc Workshop, InGoogle Scholar
  64. 64.
    Vaswani N (2009) Analyzing least squares and kalman filtered compressed sensing. In: IEEE Intl Conf Acoustics, Speech, Sig Proc (ICASSP)Google Scholar
  65. 65.
    Foucart S, Lai MJ (2009) Sparsest solutions of underdetermined linear systems via ell-q-minimization for 0<= q<= 1. Appl Comput Harmonic Anal 26:395–407MathSciNetCrossRefMATHGoogle Scholar
  66. 66.
    Jacques L (2009) A short note on compressed sensing with partially known signal support. ArXiv, preprint 0908.0660Google Scholar
  67. 67.
    Cevher V, Sankaranarayanan A, Duarte M, Reddy D, Baraniuk R, Chellappa R (2008) Compressive sensing for background subtraction. In: Eur Conf Comp Vis (ECCV)Google Scholar
  68. 68.
    Qiu C, Vaswani N (2010) Real-time robust principal components’ pursuit. Allerton Conf on Communications, Control and, ComputingGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  1. 1.Department of Electrical and Computer EngineeringIowa State UniversityAmesUSA

Personalised recommendations