ETRI Journal

Electronics and Telecommunications Research Institute (한국전자통신연구원)
권호 표지
DOI QR코드

DOI QR Code

High-throughput and low-area implementation of orthogonal matching pursuit algorithm for compressive sensing reconstruction

  • Received : 2019.02.13
  • Accepted : 2019.09.26
  • Published : 2020.06.08
Download PDF
⟨ Previous Next ⟩

Abstract

Massive computation of the reconstruction algorithm for compressive sensing (CS) has been a major concern for its real-time application. In this paper, we propose a novel high-speed architecture for the orthogonal matching pursuit (OMP) algorithm, which is the most frequently used to reconstruct compressively sensed signals. The proposed design offers a very high throughput and includes an innovative pipeline architecture and scheduling algorithm. Least-squares problem solving, which requires a huge amount of computations in the OMP, is implemented by using systolic arrays with four new processing elements. In addition, a distributed-arithmetic-based circuit for matrix multiplication is proposed to counterbalance the area overhead caused by the multi-stage pipelining. The results of logic synthesis show that the proposed design reconstructs signals nearly 19 times faster while occupying an only 1.06 times larger area than the existing designs for N = 256, M = 64, and m = 16, where N is the number of the original samples, M is the length of the measurement vector, and m is the sparsity level of the signal.

Keywords

References

  1. L. D. Donoho, For most large underdetermined systems of linear equations, the minimal 1-norm solution is also the sparsest solution, Comm. Pure Appl. Math. 59 (2006), 797-829. https://doi.org/10.1002/cpa.20132
  2. M. Davenport, The Fundamentals of compressive sensing, SigView, 2013.
  3. W. L. Chan et al., A single-pixel terahertz imaging system based on compressed sensing, Appl. Phys. Lett. 93 (2008), 121105. https://doi.org/10.1063/1.2989126
  4. U. Gamper, P. Boesiger, and S. Kozerke, Compressed sensing in dynamic MRI, Magn. Reson. Med. 59 (2008), 365-373. https://doi.org/10.1002/mrm.21477
  5. T. R. Braun, An evaluation of GPU acceleration for sparse reconstruction, in Proc. SPIE, Signal Process, Sensor Fusion, Target Recognit. XIX, Orlando, FL, USA, 2010, pp. 769715:1-15.
  6. A. Septimus and R. Steinberg, Compressive sampling hardware reconstruction, in Proc. IEEE Internat. Symp. Circuits Syst., Paris, France, 2010, pp. 3316-3319.
  7. J. L. V. M. Stanislaus and T. Mohsenin, High performance compressive sensing reconstruction hardware with QRD process, in Proc. IEEE Internat. Symp. Circuits Syst., Seoul, Rep. of Korea, 2012, pp. 29-32.
  8. W. Shi et al., An extensible and real-time compressive sensing reconstruction hardware for WBANs using OMP, in Proc. IEEE Internat. Conf. ASIC (ASICON), Shenzhen, China, Oct. 2013, pp. 1-4.
  9. Y. M. Lin et al., Low-complexity stochastic gradient pursuit algorithm and architecture for robust compressive sensing reconstruction, IEEE Trans. Signal Process. 65 (2017), 638-650. https://doi.org/10.1109/TSP.2016.2620105
  10. J. W. Jhang and Y. H. Huang, A high-SNR projection-based atom selection OMP processor for compressive sensing, IEEE Trans. Very Large Scale Integr. VLSI Syst. 24 (2016), 3477-3488. https://doi.org/10.1109/TVLSI.2016.2554401
  11. Synopsis Inc., DesignWare Building Block IP, Document Overview, DWBB_201312.2, I-2013.12-SP2, 2014.