Automatic ship identification in ISAR imagery: an on-line system using CMSM

Abstract

We have developed an on-line system which automatically identifies ships observed in a rapidly updating sequence of range-Doppler images produced by inverse synthetic aperture radar (ISAR). In order to cope with the invariable noise due to the physics of imaging, we propose to employ a multiframe image processing algorithm which stably extracts the profile as a basic feature reflecting the entire characteristics of a target. For ship identification, representing the extracted profiles as high-dimension vectors, we adapt vector analysis using the recently proposed constrained mutual subspace method (CMSM). The system currently works on an ordinary PC at 5 frames/sec and achieves a feasible identification performance. The system is verified using simulated data.