volume | PIER Journals

2013-03-18

Feature Extraction for Landmine Detection in UWB SAR via Swd and Isomap

Jun Lou,

Dr. Jun Lou

School of Electronic Science and Engineering

National University of Defense Technology

China

Homepage

Tian Jin,

Dr. Tian Jin

School of Electronic Science and Engineering

National University of Defense Technology

China

Homepage

Zhimin Zhou

Dr. Zhimin Zhou

School of Electronic Science and Engineering

National University of Defense Technology, NUDT

China

Homepage

Progress In Electromagnetics Research, Vol. 138, 157-171, 2013

doi:10.2528/PIER12121301

Abstract

Ultra-wideband synthetic aperture radar (UWB SAR) is a sufficient approach to detect landmines over large areas from a safe standoff distance. Feature extraction is the key step of landmine detection processing. On one hand, the feature vector should contain more scattering characteristics to discriminate landmines from clutters; on the other hand, the dimension of feature vector should be lower to avoid the "curse of dimensionality". In this paper, a novel feature vector extraction method is proposed. We first obtain the scattering information in the four-dimensional domain, i.e., range, azimuth, frequency and aspect-angle, via the space-wavenumber distribution (SWD). Since the data after SWD are with higher dimension and local nonlinear structures, a typical manifold learning method, Isomap, is used to reduce the dimension. The validity of the proposed method is proved by using the real data collected by an airship-borne UWB SAR system.

Citation

Copy Export

Jun Lou, Tian Jin, and Zhimin Zhou, "Feature Extraction for Landmine Detection in UWB SAR via Swd and Isomap," Progress In Electromagnetics Research, Vol. 138, 157-171, 2013.
doi:10.2528/PIER12121301

References

1. Andrieu, J., F. Gallais, V. Mallepeyre, V. Bertrand, B. Beillard, and B. Jecko, "Land mine detection with an ultra-wideband SAR system," Proceedings of SPIE,, Vol. 4742, 237-247, 2002.
doi:10.1117/12.479094

Download Full Article (272) View Full Article volume