DocumentCode :
641907
Title :
Adaptive threshold backtracking matching pursuit for compressive sensing
Author :
Zhao Hao ; Zhang Gong
Author_Institution :
Coll. of Electron. & Inf. Eng., Nanjing Univ. of Aeronaut. & Astronaut., Nanjing, China
fYear :
2013
fDate :
14-16 April 2013
Firstpage :
1
Lastpage :
4
Abstract :
Compressive sensing (CS) is a sampling technique designed for reducing the complexity of sparse data acquisition. In this paper, a modified Orthogonal Matching Pursuit (OMP) method, called Adaptive Threshold Backtracking OMP (ATBOMP) for compressive sensing and sparse signal reconstruction is presented. Compared with the standard OMP algorithm, the ATBOMP method incorporates an adaptive threshold technique to choose candidate set and ensure the support set´s reliability by regularized procession. Through this modification, the ATBOMP method improves the reconstruction probability of the sparse signal and achieves superior performance. Also, the ATBOMP method does not require the sparsity level to be known as a priori. The experiments demonstrate the proposed method´s superior performance to that of several other OMP-type and l1 optimization methods.
Keywords :
compressed sensing; data acquisition; adaptive threshold backtracking matching pursuit; adaptive threshold technique; compressive sensing; orthogonal matching pursuit; sparse data acquisition; sparse signal reconstruction; Compressive Sensing; Orthogonal Matching Pursuit; Sparse Signal Reconstruction; threshold;
fLanguage :
English
Publisher :
iet
Conference_Titel :
Radar Conference 2013, IET International
Conference_Location :
Xi´an
Electronic_ISBN :
978-1-84919-603-1
Type :
conf
DOI :
10.1049/cp.2013.0495
Filename :
6624659
Link To Document :
بازگشت