CGSANet: A Contour-Guided and Local Structure-Aware Encoder-Decoder Network for Accurate Building Extraction From Very High-Resolution Remote Sensing Imagery

Extracting buildings accurately from very high-resolution (VHR) remote sensing imagery is challenging due to diverse building appearances, spectral variability, and complex background in VHR remote sensing images. Recent studies mainly adopt a variant of the fully convolutional network (FCN) with an...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE journal of selected topics in applied earth observations and remote sensing Jg. 15; S. 1526 - 1542
Hauptverfasser:	Chen, Shanxiong, Shi, Wenzhong, Zhou, Mingting, Zhang, Min, Xuan, Zhaoxin
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Piscataway IEEE 2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Algorithms Boundaries Building extraction Buildings Coders Contours Convolutional neural networks Data mining Datasets Feature extraction fully convolutional network (FCN) High resolution hybrid loss function Image resolution Imagery Localization Modules multitask learning Remote sensing Resolution Semantics Shape very high resolution (VHR) remote sensing imagery
ISSN:	1939-1404, 2151-1535
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!