Neural Network Based Edge Detection In Two-Look And Dual-Polarization Radar Images

A.V. Naumenko (1) , V.V. Lukin (1) , Benoît Vozel (2) , Kacem Chehdi (2) , K. Egiazarian (3)

1 Kharkov National University
2 IETR - Institut d'Électronique et des Technologies du numéRique
3 Department of Signal Processing [Tampere]

Mots clés: single-look mode; edge detection; radar computing; radar imaging; radar polarimetry; synthetic aperture radar; neural nets; dual-polarization radar images; SAR image pre-filtering; NN edge detector; area under the curve; image processing; neural network based edge detection; two-look radar images; Artificial neural networks; Detectors; Image edge detection; Noise; Speckle; Training; neural network; two-look images; real-life TerraSAR-X data; parameter optimization; polarimetric

Domaines: Traitement du signal et de l'image [eess.SP]

A.V. Naumenko, V.V. Lukin, Benoît Vozel, Kacem Chehdi, K. Egiazarian. Neural Network Based Edge Detection In Two-Look And Dual-Polarization Radar Images. 15th International Radar Symposium (IRS), Jun 2014, Gdansk, Poland. http://www.ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6869302&isnumber=6869176, ⟨10.1109/IRS.2014.6869302⟩. ⟨hal-01111028⟩