Robust SAR ATR on MSTAR with Deep Learning Models trained on Full Synthetic MOCEM data - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

Robust SAR ATR on MSTAR with Deep Learning Models trained on Full Synthetic MOCEM data

Benjamin Camus
  • Fonction : Auteur
  • PersonId : 1136354
Corentin Le Barbu
Eric Monteux
  • Fonction : Auteur
  • PersonId : 1136355

Résumé

The promising potential of Deep Learning for Automatic Target Recognition (ATR) on Synthetic Aperture Radar (SAR) images vanishes when considering the complexity of collecting training datasets measurements. Simulation can overcome this issue by producing synthetic training datasets. However, because of the limited representativeness of simulation, models trained in a classical way with synthetic images have limited generalization abilities when dealing with real measurement at test time. Previous works identified a set of equally promising deep-learning algorithms to tackle this issue. However, these approaches have been evaluated in a very favorable scenario with a synthetic training dataset that overfits the ground truth of the measured test data. In this work, we study the ATR problem outside of this ideal condition, which is unlikely to occur in real operational contexts. Our contribution is threefold. (1) Using the MOCEM simulator (developed by SCALIAN DS for the French MoD/DGA), we produce a synthetic MSTAR training dataset that differs significantly from the real measurements. (2) We experimentally demonstrate the limits of the state-of-the-art. (3) We show that domain randomization techniques and adversarial training can be combined to overcome this issue. We demonstrate that this approach is more robust than the state-of-the-art, with an accuracy of 75 %, while having a limited impact on computing performance during training.
Fichier principal
Vignette du fichier
Scalian_CAID2022_submitted_version.pdf (1.08 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03694957 , version 1 (14-06-2022)

Licence

Paternité - Pas d'utilisation commerciale

Identifiants

Citer

Benjamin Camus, Corentin Le Barbu, Eric Monteux. Robust SAR ATR on MSTAR with Deep Learning Models trained on Full Synthetic MOCEM data. 2022. ⟨hal-03694957⟩

Collections

TDS-MACS
40 Consultations
131 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More