GroupNet: Learning to group corner for object detection in remote sensing imagery

doi:10.1016/j.cja.2021.09.0161000-9361

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

	GroupNet: Learning to group corner for object detection in remote sensing imagery
	Ni, Lei 1,3; Huo, Chunlei2 ; Zhang, Xin2 ; Wang, Peng1 ; Zhou, Zhixin 1
发表期刊	CHINESE JOURNAL OF AERONAUTICS
ISSN	1000-9361
	2022-06-01
卷号	35 期号:6 页码:273-284
通讯作者	Zhou, Zhixin(zxzhou@cashq.ac.cn)
摘要	Due to the attractive potential in avoiding the elaborate definition of anchor attributes, anchor-free-based deep learning approaches are promising for object detection in remote sensing imagery. CornerNet is one of the most representative methods in anchor-free-based deep learning approaches. However, it can be observed distinctly from the visual inspection that the CornerNet is limited in grouping keypoints, which significantly impacts the detection performance. To address the above problem, a novel and effective approach, called GroupNet, is presented in this paper, which adaptively groups corner specific to the objects based on corner embedding vector and corner grouping network. Compared with the CornerNet, the proposed approach is more effective in learning the semantic relationship between corners and improving remarkably the detection performance. On NWPU dataset, experiments demonstrate that our GroupNet not only outperforms the CornerNet with an AP of 12.8%, but also achieves comparable performance to considerable approaches with 83.4% AP. (c) 2021 Chinese Society of Aeronautics and Astronautics. Production and hosting by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
关键词	CornerNet Feature representation Multi-dimension embedding Object detection Remote sensing
DOI	10.1016/j.cja.2021.09.0161000-9361
收录类别	SCI
语种	英语
资助项目	Natural Science Foundation of China[62071466]
项目资助者	Natural Science Foundation of China
WOS研究方向	Engineering
WOS类目	Engineering, Aerospace
WOS记录号	WOS:000795163800007
出版者	ELSEVIER SCIENCE INC
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/173211/49429
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	Zhou, Zhixin
作者单位	1.Space Engn Univ, Beijing 101416, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Beijing Inst Remote Sensing, Beijing 100192, Peoples R China
推荐引用方式 GB/T 7714	Ni, Lei,Huo, Chunlei,Zhang, Xin,et al. GroupNet: Learning to group corner for object detection in remote sensing imagery[J]. CHINESE JOURNAL OF AERONAUTICS,2022,35(6):273-284.
APA	Ni, Lei,Huo, Chunlei,Zhang, Xin,Wang, Peng,&Zhou, Zhixin.(2022).GroupNet: Learning to group corner for object detection in remote sensing imagery.CHINESE JOURNAL OF AERONAUTICS,35(6),273-284.
MLA	Ni, Lei,et al."GroupNet: Learning to group corner for object detection in remote sensing imagery".CHINESE JOURNAL OF AERONAUTICS 35.6(2022):273-284.