Online dictionary learning aided target recognition in cognitive GPR

Sparse decomposition of ground penetration radar (GPR) signals facilitates the use of compressed sensing techniques for faster data acquisition and enhanced feature extraction for target classification. In this paper, we investigate use of an online dictionary learning (ODL) technique in the context...

Full description

Saved in:
Bibliographic Details
Main Authors: Giovanneschi, Fabio, Mishra, Kumar Vijay, Gonzalez-Huici, Maria Antonia, Eldar, Yonina C., Ender, Joachim H. G.
Format: Conference Proceeding
Language:English
Subjects:
cognitive radar
compressed sensing
Dictionaries
Geophysical measurements
Ground penetrating radar
ground penetration radar
KSVD
Machine learning
online dictionary learning
Support vector machines
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Sparse decomposition of ground penetration radar (GPR) signals facilitates the use of compressed sensing techniques for faster data acquisition and enhanced feature extraction for target classification. In this paper, we investigate use of an online dictionary learning (ODL) technique in the context of GPR to bring down the learning time as well as improve identification of abandoned anti-personnel landmines. Our experimental results using real data from an L-band GPR for PMN/PMA2, ERA and T72 mines show that ODL reduces learning time by 94% and increases clutter detection by 10% over the classical K-SVD algorithm. Moreover, our methods could be helpful in cognitive operation of the GPR where the system adapts the range sampling based on the learned dictionary.
ISSN:2153-7003
DOI:10.1109/IGARSS.2017.8128079