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

doi:10.3390/rs14040975

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 遥感图像处理团队

	NaGAN: Nadir-like Generative Adversarial Network for Off-Nadir Object Detection of Multi-View Remote Sensing Imagery
	Ni, Lei 1,3; Huo, Chunlei 4; Zhang, Xin 4; Wang, Peng 3; Zhang, Luyang 2; Guo, Kangkang 3; Zhou, Zhixin 3
刊名	REMOTE SENSING
	2022-02-01
卷号	14 期号:4 页码:20
关键词	multi-view remote sensing imagery object detection generative adversarial network off-nadir SpaceNet
DOI	10.3390/rs14040975
通讯作者	Zhou, Zhixin(zxzhou@cashq.ac.cn)
英文摘要	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.
资助项目	National Natural Science Foundation of China[62071466] ; Guangxi Natural Science Foundation[2018GXNSFBA281086]
WOS研究方向	Environmental Sciences & Ecology ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology
语种	英语
出版者	MDPI
WOS记录号	WOS:000765158400001
资助机构	National Natural Science Foundation of China ; Guangxi Natural Science Foundation
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/48029]
专题	自动化研究所_模式识别国家重点实验室_遥感图像处理团队
通讯作者	Zhou, Zhixin
作者单位	1.Beijing Inst Remote Sensing, Beijing 100192, Peoples R China 2.Nanjing Univ Aeronaut & Astronaut, Coll Automat Engn, Nanjing 210016, Peoples R China 3.Space Engn Univ, Beijing 101416, Peoples R China 4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, 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.