SPANet: A Self-balancing Position Attention Network for Anchor-free SAR Ship Detection

Synthetic aperture radar (SAR) images of ships have complex background interference, multi-scale targets, and irregular distribution characteristics. However, existing mainstream SAR ship detection algorithms rely on manually designed hyperparameters. This results in poor robustness, which makes it...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE journal of selected topics in applied earth observations and remote sensing 2023-01, Vol.16, p.1-16
Hauptverfasser:	Chang, Hao, Fu, Xiongjun, Lu, Jihua, Guo, Kunyi, Dong, Jian, Zhao, Congxia, Feng, Cheng, Li, Ziying, Zhang, Yue
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Algorithms Anchor-free mechanism Anchors Balancing Context Convolution Detection Detection algorithms Distribution Feature extraction Information processing Interference Marine vehicles Modules Prediction algorithms Radar detection Radar imaging Radar polarimetry Robustness SAR (radar) self-attention Ships Signal processing algorithms small target detection Synthetic aperture radar synthetic aperture radar (SAR)
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!