Train in Dense and Test in Sparse: A Method for Sparse Object Detection in Aerial Images

doi:10.1109/LGRS.2020.3035844

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 先进时空数据分析与学习

	Train in Dense and Test in Sparse: A Method for Sparse Object Detection in Aerial Images
	Ding, Kun 1; He, Guojin 1; Gu, Huxiang2 ; Zhong, Zisha2 ; Xiang, Shiming2 ; Pan, Chunhong2
发表期刊	IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
ISSN	1545-598X
	2022
卷号	19 页码:5
通讯作者	Ding, Kun(kding1225@gmail.com)
摘要	Applications of aerial imaging, especially based on unmanned aerial vehicles (UAVs) platform, rapidly explode in recent years. Meanwhile, vision-based sensing, e.g., detection and recognition, for UAVs becomes increasingly important. Objects in aerial images are usually of tiny size, hence occupying a limited area. Terminology speaking, the images are very sparse in spatial. However, existing work in aerial object detection commonly ignores this point. Conversely, we explore the availability of such a property in improving the detection performance of aerial images. Specifically, we propose a general method, train in dense and test in sparse (TDTS), to exploit sparsity in aerial object detection: 1) in the training stage, the possible positions of object are learned by training a fully convolutional network (called prophet head) and 2) in the testing stage, prophet head identifies the possible object locations to reduce redundant computation in classification and box prediction head by sparse convolution. By extensive experiments on the VisDrone2019-Det data set, we find that the sparsity can not only help to speed up inference but also to improve accuracy. Thus, we argue that the sparsity deserves more attention.
关键词	Convolution Head Training Testing Object detection Feature extraction Real-time systems Aerial images object detection sparse convolution spatial sparsity
DOI	10.1109/LGRS.2020.3035844
关键词[WOS]	VEHICLE DETECTION
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61731022] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDA19090300]
项目资助者	National Natural Science Foundation of China ; Strategic Priority Research Program of the Chinese Academy of Sciences
WOS研究方向	Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology
WOS类目	Geochemistry & Geophysics ; Engineering, Electrical & Electronic ; Remote Sensing ; Imaging Science & Photographic Technology
WOS记录号	WOS:000733952000060
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
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：3[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/173211/47149
专题	多模态人工智能系统全国重点实验室_先进时空数据分析与学习
通讯作者	Ding, Kun
作者单位	1.Chinese Acad Sci, Aerosp Informat Res Inst, Beijing 100094, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Ding, Kun,He, Guojin,Gu, Huxiang,et al. Train in Dense and Test in Sparse: A Method for Sparse Object Detection in Aerial Images[J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,2022,19:5.
APA	Ding, Kun,He, Guojin,Gu, Huxiang,Zhong, Zisha,Xiang, Shiming,&Pan, Chunhong.(2022).Train in Dense and Test in Sparse: A Method for Sparse Object Detection in Aerial Images.IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,19,5.
MLA	Ding, Kun,et al."Train in Dense and Test in Sparse: A Method for Sparse Object Detection in Aerial Images".IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 19(2022):5.