NaGAN: Nadir-like Generative Adversarial Network for Off-Nadir Object Detection of Multi-View Remote Sensing Imagery

doi:10.3390/rs14040975

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

	NaGAN: Nadir-like Generative Adversarial Network for Off-Nadir Object Detection of Multi-View Remote Sensing Imagery
	Ni, Lei 1,2; Huo, Chunlei3 ; Zhang, Xin3 ; Wang, Peng 1; Zhang, Luyang 4; Guo, Kangkang 1; Zhou, Zhixin 1
发表期刊	REMOTE SENSING
	2022-02-01
卷号	14 期号:4 页码:20
通讯作者	Zhou, Zhixin(zxzhou@cashq.ac.cn)
摘要	Detecting off-nadir objects is a well-known challenge in remote sensing due to the distortion and mutable representation. Existing methods mainly focus on a narrow range of view angles, and they ignore broad-view pantoscopic remote sensing imagery. To address the off-nadir object detection problem in remote sensing, a new nadir-like generative adversarial network (NaGAN) is proposed in this paper by narrowing the representation differences between the off-nadir and nadir object. NaGAN consists of a generator and a discriminator, in which the generator learns to transform the off-nadir object to a nadir-like one so that they are difficult to discriminate by the discriminator, and the discriminator competes with the generator to learn more nadir-like features. With the progressive competition between the generator and discriminator, the performances of off-nadir object detection are improved significantly. Extensive evaluations on the challenging SpaceNet benchmark for remote sensing demonstrate the superiority of NaGAN to the well-established state-of-the-art in detecting off-nadir objects.
关键词	multi-view remote sensing imagery object detection generative adversarial network off-nadir SpaceNet
DOI	10.3390/rs14040975
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62071466] ; Guangxi Natural Science Foundation[2018GXNSFBA281086]
项目资助者	National Natural Science Foundation of China ; Guangxi Natural Science Foundation
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:000765158400001
出版者	MDPI
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/48030
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.Beijing Inst Remote Sensing, Beijing 100192, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 4.Nanjing Univ Aeronaut & Astronaut, Coll Automat Engn, Nanjing 210016, Peoples R China
推荐引用方式 GB/T 7714	Ni, Lei,Huo, Chunlei,Zhang, Xin,et al. NaGAN: Nadir-like Generative Adversarial Network for Off-Nadir Object Detection of Multi-View Remote Sensing Imagery[J]. REMOTE SENSING,2022,14(4):20.
APA	Ni, Lei.,Huo, Chunlei.,Zhang, Xin.,Wang, Peng.,Zhang, Luyang.,...&Zhou, Zhixin.(2022).NaGAN: Nadir-like Generative Adversarial Network for Off-Nadir Object Detection of Multi-View Remote Sensing Imagery.REMOTE SENSING,14(4),20.
MLA	Ni, Lei,et al."NaGAN: Nadir-like Generative Adversarial Network for Off-Nadir Object Detection of Multi-View Remote Sensing Imagery".REMOTE SENSING 14.4(2022):20.