Subspace pursuit embedded in orthogonal matching pursuit
2012 (English)In: TENCON 2012 - 2012 IEEE Region 10 Conference, IEEE , 2012, 6412325- p.Conference paper (Refereed)
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.
Place, publisher, year, edition, pages
IEEE , 2012. 6412325- p.
Compressed sensing, Greedy Pursuits, Sparse Recovery
Engineering and Technology
IdentifiersURN: urn:nbn:se:kth:diva-118767DOI: 10.1109/TENCON.2012.6412325ScopusID: 2-s2.0-84873943598ISBN: 978-146734822-5OAI: oai:DiVA.org:kth-118767DiVA: diva2:608129
2012 IEEE Region 10 Conference: Sustainable Development Through Humanitarian Technology, TENCON 2012, 19 November 2012 through 22 November 2012, Cebu
QC 201302262013-02-262013-02-262013-02-26Bibliographically approved