Multi-Scale Feature Integrated Attention-Based Rotation Network for Object Detection in VHR Aerial Images

doi:10.3390/s20061686

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 智能机器人系统研究

	Multi-Scale Feature Integrated Attention-Based Rotation Network for Object Detection in VHR Aerial Images
	Yang, Feng 1; Li, Wentong 1; Hu, Haiwei 1; Li, Wanyi2 ; Wang, Peng2
发表期刊	SENSORS
	2020-03-01
卷号	20 期号:6 页码:21
通讯作者	Yang, Feng(yangfeng@nwpu.edu.cn) ; Li, Wanyi(wanyi.li@ia.ac.cn)
摘要	Accurate and robust detection of multi-class objects in very high resolution (VHR) aerial images has been playing a significant role in many real-world applications. The traditional detection methods have made remarkable progresses with horizontal bounding boxes (HBBs) due to CNNs. However, HBB detection methods still exhibit limitations including the missed detection and the redundant detection regions, especially for densely-distributed and strip-like objects. Besides, large scale variations and diverse background also bring in many challenges. Aiming to address these problems, an effective region-based object detection framework named Multi-scale Feature Integration Attention Rotation Network (MFIAR-Net) is proposed for aerial images with oriented bounding boxes (OBBs), which promotes the integration of the inherent multi-scale pyramid features to generate a discriminative feature map. Meanwhile, the double-path feature attention network supervised by the mask information of ground truth is introduced to guide the network to focus on object regions and suppress the irrelevant noise. To boost the rotation regression and classification performance, we present a robust Rotation Detection Network, which can generate efficient OBB representation. Extensive experiments and comprehensive evaluations on two publicly available datasets demonstrate the effectiveness of the proposed framework.
关键词	object detection aerial images feature attention convolutional neural networks (CNNs)
DOI	10.3390/s20061686
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61771471] ; National Natural Science Foundation of China[91748131] ; Natural Science Foundation of Shaanxi province[2018MJ6048] ; Foundation of CETC Key Laboratory of Data Link Technology[20182316] ; Foundation of CETC Key Laboratory of Data Link Technology[20182203] ; Seed Foundation of Innovation and Creation for Graduate Students in Northwestern Polytechnical University[ZZ2019178]
项目资助者	National Natural Science Foundation of China ; Natural Science Foundation of Shaanxi province ; Foundation of CETC Key Laboratory of Data Link Technology ; Seed Foundation of Innovation and Creation for Graduate Students in Northwestern Polytechnical University
WOS研究方向	Chemistry ; Engineering ; Instruments & Instrumentation
WOS类目	Chemistry, Analytical ; Engineering, Electrical & Electronic ; Instruments & Instrumentation
WOS记录号	WOS:000529139700145
出版者	MDPI
七大方向——子方向分类	目标检测、跟踪与识别
引用统计	被引频次：31[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/39394
专题	多模态人工智能系统全国重点实验室_智能机器人系统研究
通讯作者	Yang, Feng; Li, Wanyi
作者单位	1.Northwestern Polytech Univ, Minist Educ, Key Lab Informat Fus Technol, Xian 710100, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Yang, Feng,Li, Wentong,Hu, Haiwei,et al. Multi-Scale Feature Integrated Attention-Based Rotation Network for Object Detection in VHR Aerial Images[J]. SENSORS,2020,20(6):21.
APA	Yang, Feng,Li, Wentong,Hu, Haiwei,Li, Wanyi,&Wang, Peng.(2020).Multi-Scale Feature Integrated Attention-Based Rotation Network for Object Detection in VHR Aerial Images.SENSORS,20(6),21.
MLA	Yang, Feng,et al."Multi-Scale Feature Integrated Attention-Based Rotation Network for Object Detection in VHR Aerial Images".SENSORS 20.6(2020):21.