Abstract :
Time-frequency analysis techniques are used for buried plastic landmine detection with a forward-looking ground penetration radar (GPR) system. Several time-frequency distributions are considered to characterise and interpret the scattering phenomena of both targets and clutter. An ambiguity function based detector is also presented, which employs principal component analysis and feature selection for data dimensionality reduction and linear discriminant analysis for signal classification. Experimental results based on the SRI (Stanford Research Institute) experimentally measured forward-looking GPR data are presented, showing a significant detection performance improvement over the conventional detector
Keywords :
feature extraction <plastic landmine detect. via forward-looking ground penetrating radar, time-freq. anal.>; image classification <plastic landmine detect. via forward-looking ground penetrating radar, time-freq. anal.>; landmine detection <plastic landmine detect. via forward-looking ground penetrating radar, time-freq. anal.>; principal component analysis <plastic landmine detect. via forward-looking ground penetrating radar, time-freq. anal.>; radar clutter <plastic landmine detect. via forward-looking ground penetrating radar, time-freq. anal.>; radar detection <plastic landmine detect. via forward-looking ground penetrating radar, time-freq. anal.>; radar imaging <plastic landmine detect. via forward-looking ground penetrating radar, time-freq. anal.>; synthetic aperture radar <plastic landmine detect. via forward-looking ground penetrating radar, time-freq. anal.>; time-frequency analysis <plastic landmine detect. via forward-looking ground penetrating radar, time-freq. anal.>; AWGN; GPR system; SAR image; SRI; Stanford Research Institute; additive white Gaussian noise; ambiguity function based detector; buried plastic landmine detection; data dimensionality reduction; detection performance; feature selection; forward-looking GPR data; forward-looking ground penetrating radar; forward-looking ground penetration radar; linear discriminant analysis; principal component analysis; radar clutter; scattering phenomena; signal classification; time-frequency analysis; time-frequency distributions;
