Algorithm/Hardware Codesign for Real-Time On-Satellite CNN-Based Ship Detection in SAR Imagery

Recently, the convolutional neural network (CNN)-based approach for on-satellite ship detection in synthetic aperture radar (SAR) images has received increasing attention since it does not rely on predefined imagery features and distributions that are required in conventional detection methods. To a...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on geoscience and remote sensing 2022, Vol.60, p.1-18
Hauptverfasser:	Yang, Geng, Lei, Jie, Xie, Weiying, Fang, Zhenman, Li, Yunsong, Wang, Jiaxuan, Zhang, Xin
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Adaptation models Algorithm/hardware codesign Algorithms Artificial neural networks Co-design Components Computer applications Constraints Convolutional neural networks convolutional neural network~(CNN) acceleration Detection Domains Feature extraction Field programmable gate arrays Hardware hardware-guided pruning High level synthesis Imagery Interlayers Libraries Marine vehicles Methods Neural networks Object recognition Power consumption Radar detection Radar imaging Radar polarimetry Real time SAR (radar) Satellites ship detection Streaming Synthetic aperture radar synthetic aperture radar~(SAR) imagery
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!