TY - GEN
T1 - GPR signal classification with low-rank and convolutional sparse coding representation
AU - Tivive, Fok Hing Chi
AU - Bouzerdoum, Abdesselam
AU - Abeynayake, Canicious
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/6/7
Y1 - 2017/6/7
N2 - This paper presents a method for target detection and classification of improvised explosive devices (IEDs), based on a joint low-rank and sparse decomposition of ground penetrating radar (GPR) signals. First the acquired GPR signals are decomposed into a low-rank component, containing the background clutter and the ground surface reflections, and a set of convolutional sparse codes, representing the target signals. Then, features are extracted from each reconstructed signal and classified using support vector machines. Experiments are conducted with real data acquired in the wild from 18 types of IEDs. Experimental results are presented which show that individual GPR traces can be classified with 73.8% accuracy. Furthermore, the IED type can be identified with 84.2% accuracy by combining individual signal classifications.
AB - This paper presents a method for target detection and classification of improvised explosive devices (IEDs), based on a joint low-rank and sparse decomposition of ground penetrating radar (GPR) signals. First the acquired GPR signals are decomposed into a low-rank component, containing the background clutter and the ground surface reflections, and a set of convolutional sparse codes, representing the target signals. Then, features are extracted from each reconstructed signal and classified using support vector machines. Experiments are conducted with real data acquired in the wild from 18 types of IEDs. Experimental results are presented which show that individual GPR traces can be classified with 73.8% accuracy. Furthermore, the IED type can be identified with 84.2% accuracy by combining individual signal classifications.
KW - Cepstrum features
KW - GPR signal classification
KW - Low-rank and sparse decomposition
KW - SVM
UR - http://www.scopus.com/inward/record.url?scp=85021412045&partnerID=8YFLogxK
U2 - 10.1109/RADAR.2017.7944416
DO - 10.1109/RADAR.2017.7944416
M3 - Conference contribution
AN - SCOPUS:85021412045
T3 - 2017 IEEE Radar Conference, RadarConf 2017
SP - 1352
EP - 1356
BT - 2017 IEEE Radar Conference, RadarConf 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 IEEE Radar Conference, RadarConf 2017
Y2 - 8 May 2017 through 12 May 2017
ER -