FEA-Swin: Foreground Enhancement Attention Swin Transformer Network for Accurate UAV-Based Dense Object Detection

doi:10.3390/s22186993

HFCAS OpenIR

	FEA-Swin: Foreground Enhancement Attention Swin Transformer Network for Accurate UAV-Based Dense Object Detection
	Xu, Wenyu 1,2; Zhang, Chaofan 1; Wang, Qi 1,2; Dai, Pangda 1
	2022-09-01
发表期刊	SENSORS
通讯作者	Zhang, Chaofan(zcfan@aiofm.ac.cn) ; Dai, Pangda(pddai@aiofm.ac.cn)
摘要	UAV-based object detection has recently attracted a lot of attention due to its diverse applications. Most of the existing convolution neural network based object detection models can perform well in common object detection cases. However, due to the fact that objects in UAV images are spatially distributed in a very dense manner, these methods have limited performance for UAV-based object detection. In this paper, we propose a novel transformer-based object detection model to improve the accuracy of object detection in UAV images. To detect dense objects competently, an advanced foreground enhancement attention Swin Transformer (FEA-Swin) framework is designed by integrating context information into the original backbone of a Swin Transformer. Moreover, to avoid the loss of information of small objects, an improved weighted bidirectional feature pyramid network (BiFPN) is presented by designing the skip connection operation. The proposed method aggregates feature maps from four stages and keeps abundant information of small objects. Specifically, to balance the detection accuracy and efficiency, we introduce an efficient neck of the BiFPN network by removing a redundant network layer. Experimental results on both public datasets and a self-made dataset demonstrate the performance of our method compared to the state-of-the-art methods in terms of detection accuracy.
关键词	object detection aerial images transformer-based foreground enhancement attention improved bidirectional feature pyramid network
DOI	10.3390/s22186993
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62102395] ; Natural Science Foundation of Anhui Province of China[2108085QF277]
项目资助者	National Natural Science Foundation of China ; Natural Science Foundation of Anhui Province of China
WOS研究方向	Chemistry ; Engineering ; Instruments & Instrumentation
WOS类目	Chemistry, Analytical ; Engineering, Electrical & Electronic ; Instruments & Instrumentation
WOS记录号	WOS:000857550700001
出版者	MDPI
引用统计	被引频次：8[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.hfcas.ac.cn:8080/handle/334002/128989
专题	中国科学院合肥物质科学研究院
通讯作者	Zhang, Chaofan; Dai, Pangda
作者单位	1.Chinese Acad Sci, Hefei Inst Phys Sci, Hefei 230031, Peoples R China 2.Univ Sci & Technol China, Grad Sch, Sci Isl Branch, Hefei 230026, Peoples R China
推荐引用方式 GB/T 7714	Xu, Wenyu,Zhang, Chaofan,Wang, Qi,et al. FEA-Swin: Foreground Enhancement Attention Swin Transformer Network for Accurate UAV-Based Dense Object Detection[J]. SENSORS,2022,22.
APA	Xu, Wenyu,Zhang, Chaofan,Wang, Qi,&Dai, Pangda.(2022).FEA-Swin: Foreground Enhancement Attention Swin Transformer Network for Accurate UAV-Based Dense Object Detection.SENSORS,22.
MLA	Xu, Wenyu,et al."FEA-Swin: Foreground Enhancement Attention Swin Transformer Network for Accurate UAV-Based Dense Object Detection".SENSORS 22(2022).