Semisupervised Pair-Wise Band Selection for Hyperspectral Images

doi:10.1109/JSTARS.2015.2424433

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

	Semisupervised Pair-Wise Band Selection for Hyperspectral Images
	Bai, Jun; Xiang, Shiming; Shi, Limin; Pan, Chunhong
发表期刊	IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
	2015-06-01
卷号	8 期号:6 页码:2798-2813
文章类型	Article
摘要	This paper proposes a new approach of band selection for classifying multiple objects in hyperspectral images. Different from traditional algorithms, we construct a semisupervised pair-wise band selection (PWBS) framework for this task, in which an individual band selection process is performed only for each pair of classes. First, the statistical parameters for spectral features of each class, including mean vectors and covariance matrices, are estimated by an expectation maximization approach in a semisupervised learning setting, where both labeled and unlabeled samples are employed for better performance. For each pair of classes, based on the estimated statistical parameters, Bhattacharyya distances between the two classes are calculated to evaluate all possible subsets of bands for classification. Second, as our proposed semisupervised framework, the PWBS followed by a binary classifier can be embedded into the semisupervised expectation maximization process to obtain posterior probabilities of samples on the selected bands. Finally, to evaluate the selected bands, all of the binary decisions obtained with multiple binary classifiers are finally fused together. Comparative experimental results demonstrate the validity of our proposed algorithm. The experimental results also prove that our band selection algorithm can perform well when the training set is very small.
关键词	Band Selection Classification Hyperspecral Remote Sensing Semisupervised
WOS标题词	Science & Technology ; Technology ; Physical Sciences
DOI	10.1109/JSTARS.2015.2424433
关键词[WOS]	SUPPORT VECTOR MACHINES ; DIMENSIONALITY REDUCTION ; MORPHOLOGICAL PROFILES ; DISCRIMINANT-ANALYSIS ; CLASSIFICATION ; SVM ; INFORMATION ; PARAMETERS ; REGRESSION ; ALGORITHM
收录类别	SCI
语种	英语
WOS研究方向	Engineering ; Physical Geography ; Remote Sensing ; Imaging Science & Photographic Technology
WOS类目	Engineering, Electrical & Electronic ; Geography, Physical ; Remote Sensing ; Imaging Science & Photographic Technology
WOS记录号	WOS:000359264000042
引用统计	被引频次：21[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/173211/8902
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
作者单位	Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Bai, Jun,Xiang, Shiming,Shi, Limin,et al. Semisupervised Pair-Wise Band Selection for Hyperspectral Images[J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,2015,8(6):2798-2813.
APA	Bai, Jun,Xiang, Shiming,Shi, Limin,&Pan, Chunhong.(2015).Semisupervised Pair-Wise Band Selection for Hyperspectral Images.IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,8(6),2798-2813.
MLA	Bai, Jun,et al."Semisupervised Pair-Wise Band Selection for Hyperspectral Images".IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 8.6(2015):2798-2813.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Semisupervised Pair-（2391KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载