Ship Detection in SAR Images Using Convolutional Variational Autoencoders

We propose an unsupervised framework for ship detection in SAR image data, based on anomaly detection. We first learn representations of the SAR images with a convolutional Variational Autoencoder. Aftwerwards, we perform anomaly detection based on those representations, with a clustering algorithm....

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE International Geoscience and Remote Sensing Symposium proceedings S. 2503 - 2506
Hauptverfasser: Ferreira, Nuno, Silveira, Margarida
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 26.09.2020
Schlagworte:
Data models
Decoding
Image reconstruction
Marine vehicles
Radar polarimetry
ship detection
Synthetic aperture radar
Training
unsupervised learning
Variational autoencoders
ISSN:2153-7003
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We propose an unsupervised framework for ship detection in SAR image data, based on anomaly detection. We first learn representations of the SAR images with a convolutional Variational Autoencoder. Aftwerwards, we perform anomaly detection based on those representations, with a clustering algorithm. Experimental results with real SAR data are provided to illustrate the performance of the proposed algorithm.
ISSN:2153-7003
DOI:10.1109/IGARSS39084.2020.9324389