TY - GEN
T1 - SVM based target classification using RCS feature vectors
AU - Bufler, Travis Dale
AU - Narayanan, Ram Mohan
AU - Dogaru, Traian
N1 - Publisher Copyright:
© 2015 SPIE.
PY - 2015
Y1 - 2015
N2 - This paper investigates the application of SVM (Support Vector Machines) for the classification of stationary human targets and indoor clutter via spectral features. Applying Finite Difference Time Domain (FDTD) techniques allows us to examine the radar cross section (RCS) of humans and indoor clutter objects by utilizing different types of computer models. FDTD allows for the spectral characteristics to be acquired over a wide range of frequencies, polarizations, aspect angles, and materials. The acquired target and clutter RCS spectral characteristics are then investigated in terms of their potential for target classification using SVMs. Based upon variables such as frequency and polarization, a SVM classifier can be trained to classify unknown targets as a human or clutter. Furthermore, the application of feature selection is applied to the spectral characteristics to determine the SVM classification accuracy of a reduced dataset. Classification accuracies of nearly 90% are achieved using radial and polynomial kernels.
AB - This paper investigates the application of SVM (Support Vector Machines) for the classification of stationary human targets and indoor clutter via spectral features. Applying Finite Difference Time Domain (FDTD) techniques allows us to examine the radar cross section (RCS) of humans and indoor clutter objects by utilizing different types of computer models. FDTD allows for the spectral characteristics to be acquired over a wide range of frequencies, polarizations, aspect angles, and materials. The acquired target and clutter RCS spectral characteristics are then investigated in terms of their potential for target classification using SVMs. Based upon variables such as frequency and polarization, a SVM classifier can be trained to classify unknown targets as a human or clutter. Furthermore, the application of feature selection is applied to the spectral characteristics to determine the SVM classification accuracy of a reduced dataset. Classification accuracies of nearly 90% are achieved using radial and polynomial kernels.
UR - http://www.scopus.com/inward/record.url?scp=84954052308&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84954052308&partnerID=8YFLogxK
U2 - 10.1117/12.2176759
DO - 10.1117/12.2176759
M3 - Conference contribution
AN - SCOPUS:84954052308
T3 - Proceedings of SPIE - The International Society for Optical Engineering
BT - Radar Sensor Technology XIX; and Active and Passive Signatures VI
A2 - Doerry, Armin
A2 - Hawley, Chadwick Todd
A2 - Gilbreath, G. Charmaine
A2 - Ranney, Kenneth I.
PB - SPIE
T2 - Radar Sensor Technology XIX; and Active and Passive Signatures VI
Y2 - 20 April 2015 through 23 April 2015
ER -