SFRE-Net: Scattering Feature Relation Enhancement Network for Aircraft Detection in SAR Images

Aircraft detection in synthetic aperture radar (SAR) images is a challenging task due to the discreteness of aircraft scattering characteristics, the diversity of aircraft size, and the interference of complex backgrounds. To address these problems, we propose a novel scattering feature relation enh...

Full description

Saved in:
Bibliographic Details
Published inRemote sensing (Basel, Switzerland) Vol. 14; no. 9; p. 2076
Main Authors Zhang, Peng, Xu, Hao, Tian, Tian, Gao, Peng, Tian, Jinwen
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.05.2022
Subjects
Accuracy
adaptive feature fusion
Aircraft
Aircraft detection
Algorithms
contextual coordinate attention
Deep learning
Design
False alarms
Feature extraction
Image enhancement
Information processing
Modules
Radar detection
Radar imaging
Receptive field
Remote sensing
Scattering
scattering point relation
Semantics
Sensors
Synthetic aperture radar
Teaching methods
Online AccessGet full text

Cover

More Information
Summary:Aircraft detection in synthetic aperture radar (SAR) images is a challenging task due to the discreteness of aircraft scattering characteristics, the diversity of aircraft size, and the interference of complex backgrounds. To address these problems, we propose a novel scattering feature relation enhancement network (SFRE-Net) in this paper. Firstly, a cascade transformer block (TRsB) structure is adopted to improve the integrity of aircraft detection results by modeling the correlation between feature points. Secondly, a feature-adaptive fusion pyramid structure (FAFP) is proposed to aggregate features of different levels and scales, enable the network to autonomously extract useful semantic information, and improve the multi-scale representation ability of the network. Thirdly, a context attention-enhancement module (CAEM) is designed to improve the positioning accuracy in complex backgrounds. Considering the discreteness of scattering characteristics, the module uses a dilated convolution pyramid structure to improve the receptive field and then captures the position of the aircraft target through the coordinate attention mechanism. Experiments on the Gaofen-3 dataset demonstrate the effectiveness of SFRE-Net with a precision rate of 94.4% and a recall rate of 94.5%.
ISSN:2072-4292
2072-4292
DOI:10.3390/rs14092076