Ambat, Sooraj K and Chatterjee, Saikat and Hari, KVS (2012) Subspace Pursuit Embedded in Orthogonal Matching Pursuit. In: IEEE Region 10 Conference (TENCON) - Sustainable Development through Humanitarian Technology, NOV 19-22, 2012 , Cebu, PHILIPPINES .
PDF
IEEE_TENCON_amb_2012.pdf - Published Version Restricted to Registered users only Download (132kB) | Request a copy |
Abstract
Orthogonal Matching Pursuit (OMP) is a popular greedy pursuit algorithm widely used for sparse signal recovery from an undersampled measurement system. However, one of the main shortcomings of OMP is its irreversible selection procedure of columns of measurement matrix. i.e., OMP does not allow removal of the columns wrongly estimated in any of the previous iterations. In this paper, we propose a modification in OMP, using the well known Subspace Pursuit (SP), to refine the subspace estimated by OMP at any iteration and hence boost the sparse signal recovery performance of OMP. Using simulations we show that the proposed scheme improves the performance of OMP in clean and noisy measurement cases.
Item Type: | Conference Proceedings |
---|---|
Series.: | TENCON IEEE Region 10 Conference Proceedings |
Publisher: | IEEE |
Additional Information: | Copyright for this article belongs to the IEEE,USA. |
Keywords: | Compressed sensing; Sparse Recovery; Greedy Pursuits |
Department/Centre: | Division of Electrical Sciences > Electrical Communication Engineering |
Date Deposited: | 04 Apr 2013 10:26 |
Last Modified: | 04 Apr 2013 10:26 |
URI: | http://eprints.iisc.ac.in/id/eprint/46340 |
Actions (login required)
View Item |