Near Real-Time Enhancement of Fractional SAR Imagery Via Adaptive Maximum Entropy Neural Network Computing

Konferenz: EUSAR 2012 - 9th European Conference on Synthetic Aperture Radar
23.04.2012 - 26.04.2012 in Nuremberg, Germany

Tagungsband: EUSAR 2012

Seiten: 4Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

Shkvarko, Yuriy V.; Santos, Stewart R.; Tuxpan, José (CINVESTAV del IPN, Mexico)

We address a neural network (NN) computing-based approach to the problem of near real-time enhancement of compressed fractional SAR imagery. The proposed approach employs the recently developed descriptive experiment design regularization (DEDR) framework for multimode image reconstruction/fusion aggregated with the variational analysis (VA) image enhancement paradigm implemented computationally via the new speeded-up adaptive maximum entropy neural network (MENN) processing technique. The developed DEDRVA- optimal MENN enhancement technique outperforms the recently proposed competing methods both in the achievable resolution enhancement and the convergence rates that is verified via reported computer simulations.