From Point to Region: Accurate and Efficient Hierarchical Small Object Detection in Low-Resolution Remote Sensing Images

doi:10.3390/rs13132620

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 三维可视计算

	From Point to Region: Accurate and Efficient Hierarchical Small Object Detection in Low-Resolution Remote Sensing Images
	Wu, Jingqian 1; Xu, Shibiao2
发表期刊	REMOTE SENSING
	2021-07-01
卷号	13 期号:13 页码:16
通讯作者	Xu, Shibiao(shibiao.xu@nlpr.ia.ac.cn)
摘要	Accurate object detection is important in computer vision. However, detecting small objects in low-resolution images remains a challenging and elusive problem, primarily because these objects are constructed of less visual information and cannot be easily distinguished from similar background regions. To resolve this problem, we propose a Hierarchical Small Object Detection Network in low-resolution remote sensing images, named HSOD-Net. We develop a point-to-region detection paradigm by first performing a key-point prediction to obtain position hypotheses, then only later super-resolving the image and detecting the objects around those candidate positions. By postponing the object prediction to after increasing its resolution, the obtained key-points are more stable than their traditional counterparts based on early object detection with less visual information. This hierarchical approach, HSOD-Net, saves significant run-time, which makes it more suitable for practical applications such as search and rescue, and drone navigation. In comparison with the state-of-art models, HSOD-Net achieves remarkable precision in detecting small objects in low-resolution remote sensing images.
关键词	small object detection key-point prediction image enhancement low resolution
DOI	10.3390/rs13132620
收录类别	SCI
语种	英语
WOS研究方向	Environmental Sciences & Ecology ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology
WOS类目	Environmental Sciences ; Geosciences, Multidisciplinary ; Remote Sensing ; Imaging Science & Photographic Technology
WOS记录号	WOS:000670955800001
出版者	MDPI
七大方向——子方向分类	三维视觉
引用统计	被引频次：5[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/173211/45278
专题	多模态人工智能系统全国重点实验室_三维可视计算
通讯作者	Xu, Shibiao
作者单位	1.Wake Forest Univ, Dept Comp Sci, Winston Salem, NC 27019 USA 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	Wu, Jingqian,Xu, Shibiao. From Point to Region: Accurate and Efficient Hierarchical Small Object Detection in Low-Resolution Remote Sensing Images[J]. REMOTE SENSING,2021,13(13):16.
APA	Wu, Jingqian,&Xu, Shibiao.(2021).From Point to Region: Accurate and Efficient Hierarchical Small Object Detection in Low-Resolution Remote Sensing Images.REMOTE SENSING,13(13),16.
MLA	Wu, Jingqian,et al."From Point to Region: Accurate and Efficient Hierarchical Small Object Detection in Low-Resolution Remote Sensing Images".REMOTE SENSING 13.13(2021):16.