SIAMESE NEURAL NETWORK FOR AUTOMATIC TARGET RECOGNITION USING SYNTHETIC APERTURE RADAR - ENSTA Bretagne - École nationale supérieure de techniques avancées Bretagne Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

SIAMESE NEURAL NETWORK FOR AUTOMATIC TARGET RECOGNITION USING SYNTHETIC APERTURE RADAR

Résumé

Automatic Target Recognition (ATR) is an interest problem in various application fields (security, surveillance, automotive, environment, medicine, communications, remote sensing, ...). Thus, SAR (Synthetic Aperture Radar) and ISAR (Inverse Synthetic Aperture Radar) radar images provide rich visual information about the observed radar target. From these radar images, several methods have been proposed to meet the expected requirements in several application domains, including target recognition, which is one of the main issues addressed in the present work. Traditional standard image classification techniques are not suitable for efficient classification of SAR images due to the limited data available in some classes (unbalanced data). To solve these problems, we introduce a deep learning model, the Siamese network with multiclass classification, built from a pre-trained model to improve the model performances on unbalanced classes. To evaluate the proposed method, the MSTAR dataset is used. The proposed method improves the recognition rate from 95,18% to 97.16%.
Fichier principal
Vignette du fichier
IGARS_4pagesv2.pdf (2.58 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04184121 , version 1 (21-08-2023)

Identifiants

  • HAL Id : hal-04184121 , version 1

Citer

Yasmine Khenchaf, Abdelmalek Toumi. SIAMESE NEURAL NETWORK FOR AUTOMATIC TARGET RECOGNITION USING SYNTHETIC APERTURE RADAR. The International Geoscience and Remote Sensing Symposium (IGARSS), IEEE Geoscience and Remote Sensing Society (GRSS), Jun 2023, Pasadena, California, United States. ⟨hal-04184121⟩
58 Consultations
46 Téléchargements

Partager

Gmail Facebook X LinkedIn More