Hyperspectral Anomaly Detection by Graph Pixel Selection

CORC > 西安光学精密机械研究所 > 中国科学院西安光学精密机械研究所 > 光学影像学习与分析中心

	Hyperspectral Anomaly Detection by Graph Pixel Selection
	Yuan, Yuan 1; Ma, Dandan 1,2; Wang, Qi 3,4
刊名	ieee transactions on cybernetics
	2016-12-01
卷号	46 期号:12 页码:3123-3134
关键词	Graph theory hyperspectral anomaly detection manifold learning
ISSN号	2168-2267
通讯作者	wang, q (reprint author), northwestern polytech univ, sch comp sci, xian 710072, peoples r china.
产权排序	1
英文摘要	hyperspectral anomaly detection (ad) is an important problem in remote sensing field. it can make full use of the spectral differences to discover certain potential interesting regions without any target priors. traditional mahalanobis-distance-based anomaly detectors assume the background spectrum distribution conforms to a gaussian distribution. however, this and other similar distributions may not be satisfied for the real hyperspectral images. moreover, the background statistics are susceptible to contamination of anomaly targets which will lead to a high false-positive rate. to address these intrinsic problems, this paper proposes a novel ad method based on the graph theory. we first construct a vertex- and edge-weighted graph and then utilize a pixel selection process to locate the anomaly targets. two contributions are claimed in this paper: 1) no background distributions are required which makes the method more adaptive and 2) both the vertex and edge weights are considered which enables a more accurate detection performance and better robustness to noise. intensive experiments on the simulated and real hyperspectral images demonstrate that the proposed method outperforms other benchmark competitors. in addition, the robustness of the proposed method has been validated by using various window sizes. this experimental result also demonstrates the valuable characteristic of less computational complexity and less parameter tuning for real applications.
学科主题	computer science, artificial intelligence ; computer science, cybernetics
WOS标题词	science & technology ; technology
类目[WOS]	computer science, artificial intelligence ; computer science, cybernetics
研究领域[WOS]	computer science
关键词[WOS]	target detection ; network security ; imagery ; classification ; algorithms ; filter
收录类别	SCI
语种	英语
WOS记录号	WOS:000388923100035
内容类型	期刊论文
源URL	[http://ir.opt.ac.cn/handle/181661/28559]
专题	西安光学精密机械研究所_光学影像学习与分析中心
作者单位	1.Chinese Acad Sci, Xian Inst Opt & Precis Mech, State Key Lab Transient Opt & Photon, Ctr Opt Imagery Anal & Learning, Xian 710119, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Northwestern Polytech Univ, Sch Comp Sci, Xian 710072, Peoples R China 4.Northwestern Polytech Univ, Ctr Opt Imagery Anal & Learning, Xian 710072, Peoples R China
推荐引用方式 GB/T 7714	Yuan, Yuan,Ma, Dandan,Wang, Qi. Hyperspectral Anomaly Detection by Graph Pixel Selection[J]. ieee transactions on cybernetics,2016,46(12):3123-3134.
APA	Yuan, Yuan,Ma, Dandan,&Wang, Qi.(2016).Hyperspectral Anomaly Detection by Graph Pixel Selection.ieee transactions on cybernetics,46(12),3123-3134.
MLA	Yuan, Yuan,et al."Hyperspectral Anomaly Detection by Graph Pixel Selection".ieee transactions on cybernetics 46.12(2016):3123-3134.