基于注意力机制特征融合网络的SAR图像飞机目标快速检测
Attention Feature Fusion Network for Rapid Aircraft Detection in SAR Images
查看参考文献25篇
文摘
|
针对合成孔径雷达(Synthetic Aperture Radar,SAR)图像中飞机目标散射点离散化程度高,周围背景干扰复杂,现有算法对飞机浅层语义特征表征能力弱等问题,本文提出了基于注意力特征融合网络(Attention Feature Fusion Network,AFFN)的SAR图像飞机目标检测算法.通过引入瓶颈注意力模块(Bottleneck Attention Module,BAM),本文在AFFN中构建了包含注意力双向特征融合模块(Attention Bidirectional Feature Fusion Module,ABFFM)与注意力传输连接模块(Attention Transfer Connection Block,ATCB)的注意力特征融合策略并合理优化了网络结构,提升了算法对飞机离散化散射点浅层语义特征的提取与判别.基于自建的Gaofen-3与TerraSAR-X卫星图像混合飞机目标实测数据集,实验对AFFN与基于深度学习的通用目标检测以及SAR图像特定目标检测算法进行了比较,其结果验证了AFFN对SAR图像飞机目标检测的准确性与高效性. |
其他语种文摘
|
Aiming at the problems of high discretization of aircraft's backscattering points, complex background interference of surroundings in Synthetic Aperture Radar (SAR) images and weak representation of shallow semantic features of aircraft by existing algorithms, an Attention Feature Fusion Network (AFFN) was proposed for aircraft detection in SAR images. By introducing Bottleneck Attention Module (BAM), this article constructed an attention feature fusion strategy consisting of Attention Bidirectional Feature Fusion Module (ABFFM) and Attention Transfer Connection Block (ATCB) in AFFN, and rationally optimized the network structure so as to strengthen the abilities of extracting and discriminating shallow semantic features of aircraft. Based on a self-built Gaofen-3 and TerraSAR-X mixed aircraft dataset, AFFN was compared with several CNN-based general object detection methods and methods designed for specific objects in SAR images. The experimental results illustrated the accuracy and effectiveness of our method for aircraft detection in SAR images. |
来源
|
电子学报
,2021,49(9):1665-1674 【核心库】
|
DOI
|
10.12263/DZXB.20200486
|
关键词
|
注意力机制
;
特征融合
;
飞机目标快速检测
;
SAR图像
;
卷积神经网络
|
地址
|
国防科技大学, 电子信息系统与复杂电磁环境效应国家重点实验室, 湖南, 长沙, 410073
|
语种
|
中文 |
文献类型
|
研究性论文 |
ISSN
|
0372-2112 |
学科
|
电子技术、通信技术 |
基金
|
国家自然科学基金
|
文献收藏号
|
CSCD:7077340
|
参考文献 共
25
共2页
|
1.
张嘉峰. Fisher纹理分布下基于匹配滤波的极化SAR图像CFAR检测方法.
电子学报,2019,47(12):2533-2543
|
CSCD被引
1
次
|
|
|
|
2.
王彬. 基于广义Gamma分布的高分辨率SAR图像海岸线检测.
电子学报,2018,46(4):827-833
|
CSCD被引
4
次
|
|
|
|
3.
魏志强. 基于深度卷积神经网络的图上半监督极化SAR图像分类算法.
电子学报,2020,48(1):66-74
|
CSCD被引
3
次
|
|
|
|
4.
Zhao Y. Attention receptive pyramid network for ship detection in SAR images.
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2020,13:2738-2756
|
CSCD被引
17
次
|
|
|
|
5.
Hu H. Aircraft Detection for HR SAR Images in Non-homogeneous Background Using GGMD-Based Modeling.
Chinese Journal of Electronics,2019,28(6):1271-1280
|
CSCD被引
2
次
|
|
|
|
6.
Zhang H. Aircraft target detection algorithm based on high resolution spaceborne SAR imagery.
MIPPR 2017: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications,2018:193-198
|
CSCD被引
1
次
|
|
|
|
7.
Tan Y H. Aircraft detection in highresolution SAR images based on a gradient textural saliency map.
Sensors,2015,15(9):23071-23094
|
CSCD被引
5
次
|
|
|
|
8.
Dou F. Aircraft recognition in high resolution SAR images using saliency map and scattering structure features.
2016 IEEE International Geoscience and Remote Sensing Symposium(IGARSS),2016:1575-1578
|
CSCD被引
1
次
|
|
|
|
9.
王思雨. 基于卷积神经网络的高分辨率SAR图像飞机目标检测方法.
雷达学报,2017,6(2):195-203
|
CSCD被引
26
次
|
|
|
|
10.
郭倩. 星载合成孔径雷达图像的飞机目标检测.
上海航天,2018,35(6):57-64
|
CSCD被引
9
次
|
|
|
|
11.
Diao W H. Aircraft detection in sar images using saliency based location regression network.
2018 IEEE International Geoscience and Remote Sensing Symposium,2018:2334-2337
|
CSCD被引
2
次
|
|
|
|
12.
Lin T Y. Focal loss for dense object detection.
2017 IEEE International Conference on Computer Vision (ICCV),2017:2999-3007
|
CSCD被引
114
次
|
|
|
|
13.
Zhao Y. Pyramid attention dilated network for aircraft detection in SAR images.
IEEE Geoscience and Remote Sensing Letters,2021,18(4):662-666
|
CSCD被引
4
次
|
|
|
|
14.
He C. A component-based multi-layer parallel network for airplane detection in SAR imagery.
Remote Sensing,2018,10(7):1016
|
CSCD被引
4
次
|
|
|
|
15.
Zhang S. Single-shot refinement neural network for object detection.
Proceedings of the IEEE conference on computer vision and pattern recognition,2018:4203-4212
|
CSCD被引
23
次
|
|
|
|
16.
Ren S Q. Faster R-CNN: Towards real-time object detection with region proposal networks.
IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149
|
CSCD被引
4396
次
|
|
|
|
17.
Cai Z W. Cascade R-CNN: Delving into high quality object detection.
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),2018:6154-6162
|
CSCD被引
1
次
|
|
|
|
18.
Lin T Y. Feature pyramid networks for object detection.
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2017:936-944
|
CSCD被引
175
次
|
|
|
|
19.
Liu W. SSD: Single shot multibox detector.
European Conference on Computer Vision (ECCV),2016:21-37
|
CSCD被引
34
次
|
|
|
|
20.
Liu S T. Receptive field block net for accurate and fast object detection.
Proceedings of the European Conference on Computer Vision (ECCV),2018:385-400
|
CSCD被引
3
次
|
|
|
|
|