Abstract :
Recognizing occluded vehicle targets in synthetic aperture radar (SAR) images is addressed. Recognition algorithms, based on local features, are presented that successfully recognize highly occluded objects in both XPATCH synthetic SAR signatures and real SAR images of actual vehicles from the MSTAR data. Extensive experimental results are presented for a basic recognition algorithm, using SAR scattering center relative locations as features with the XPATCH data and for an improved algorithm, using scatterer locations and magnitudes with the real SAR targets in the MSTAR data. The results show the effect of occlusion on recognition performance in terms of probability of correct identification, receiver operating characteristic curves, and confusion matrices
Keywords :
object recognition; radar computing; radar imaging; radar target recognition; synthetic aperture radar; MSTAR data; SAR images; XPATCH synthetic SAR signatures; confusion matrices; decision rule; local features; occluded objects recognition; occluded vehicle targets; performance analysis; positional noise; probability of correct identification; real images; receiver operating characteristic curves; recognition algorithms; scattering center relative locations; Adaptive arrays; Australia; Image recognition; Radar scattering; Radar signal processing; Signal processing algorithms; Surveillance; Synthetic aperture radar; Target recognition; Vehicles;
