Dilated Convolution and Feature Fusion SSD Network for Small Object Detection in Remote Sensing Images

Noting the shortcomings of current methods in detecting small objects in image-based remote sensing applications, in this paper, we propose a novel implementation of single shot multibox detector (SSD) networks based on dilated convolution and feature fusion. We call this algorithm dilated convoluti...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE access 2020, Vol.8, p.82832-82843
Hauptverfasser:	Qu, Junsuo, Su, Chang, Zhang, Zhiwei, Razi, Abolfazl
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Convolution Data processing Detectors DFSSD network dilated convolution Feature extraction feature fusion Feature maps Image segmentation Object detection Object recognition Remote sensing Semantics Small object detection
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!