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

• Published in: Proceedings of the 2002 IEEE Radar Conference (IEEE Cat. No.02CH37322) pp. 206 - 211
• Main Authors: Maki, A., Fukui, K., Kawawada, Y., Kiya, M.
• Format: Conference Proceeding
• Language: English
• Published: Piscataway NJ IEEE 2002
• Subjects: Applied sciences; Data mining; Exact sciences and technology; Image processing; Image reconstruction; Information, signal and communications theory; Inverse synthetic aperture radar; Marine vehicles; Physics; Principal component analysis; Radar imaging; Radiolocalization and radionavigation; Signal processing; Subspace constraints; Telecommunications; Telecommunications and information theory; Testing; Image processing; Feature extraction; Ship; Automatic recognition; Object recognition; Target detection; Synthetic aperture radar
• ISBN: 9780780373570; 078037357X
• DOI: 10.1109/NRC.2002.999720

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.