Sparse anchoring guided high-resolution capsule network for geospatial object detection from remote sensing imagery

[Display omitted] •High-resolution capsule network for semantically strong and spatially accurate feature extraction.•Capsule-based efficient self-attention module for feature quality and robustness promotion.•Sparse anchoring network for lightweight, high-quality region proposal generation.•Oriente...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International journal of applied earth observation and geoinformation Jg. 104; S. 102548
Hauptverfasser: Yu, Yongtao, Wang, Jun, Qiang, Hao, Jiang, Mingxin, Tang, E, Yu, Changhui, Zhang, Yongjun, Li, Jonathan
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 15.12.2021
Elsevier
Schlagworte:
Capsule attention
Capsule network
data collection
image interpretation
ingredients
Object recognition
Region proposal
Remote sensing imagery
Sparse anchoring
spatial data
texture
Region proposal
Object recognition
Capsule network
Capsule attention
Sparse anchoring
Remote sensing imagery
ISSN:1569-8432, 1872-826X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:[Display omitted] •High-resolution capsule network for semantically strong and spatially accurate feature extraction.•Capsule-based efficient self-attention module for feature quality and robustness promotion.•Sparse anchoring network for lightweight, high-quality region proposal generation.•Oriented region proposal generation for arbitrarily-oriented geospatial object detection. As the optical remote sensing techniques keep developing with a rapid pace, remote sensing images are positively considered in many fields. Accordingly, a great number of algorithms have been exploited for remote sensing image interpretation purposes. Thereinto, object recognition acts as an important ingredient to many applications. However, to achieve highly accurate object recognition is still challengeable caused by the orientation and size diversities, spatial distribution and density variations, shape and aspect ratio irregularities, occlusion and shadow impacts, as well as complex texture and surrounding environment changes. In this paper, a sparse anchoring guided high-resolution capsule network (SAHR-CapsNet) is proposed for geospatial object detection based on remote sensing images. First, formulated with the multibranch high-resolution capsule network architecture assisted by multiscale feature propagation and fusion, the SAHR-CapsNet can extract semantically strong and spatially accurate feature semantics at multiple scales. Second, integrated with the efficient capsule-based self-attention module, the SAHR-CapsNet functions promisingly to attend to target-specific spatial features and informative channel features. Finally, adopted with the capsule-based sparse anchoring network, the SAHR-CapsNet performs efficiently in generating a fixed number of lightweight, high-quality sparse region proposals. Quantitative assessments and comparative analyses on two challenging remote sensing image datasets demonstrate the applicability and effectiveness of the developed SAHR-CapsNet for geospatial object detection applications.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1569-8432
1872-826X
DOI:10.1016/j.jag.2021.102548