Semi-supervised kernel target detection in hyperspectral images

被引：0

作者：

Capobianco, Luca ^{[1
]}

Garzelli, Andrea ^{[1
]}

Camps-Valls, Gustavo ^{[2
]}

机构：

[1] Univ Siena, Dipartimento Ingn Informaz, Via Laterina 8, I-53100 Siena, Italy

[2] Univ Valencia, Dept Elect Engn, Valencia, Spain

来源：

2009 9TH INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS DESIGN AND APPLICATIONS | 2009年

关键词：

Machine learning; hyperspectral images; target detection; ORTHOGONAL SUBSPACE PROJECTION; ANOMALY DETECTION;

D O I：

10.1109/ISDA.2009.121

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A semi-supervised graph-based approach to target detection is presented. The proposed method improves the Kernel Orthogonal Subspace Projection (KOSP) by deforming the kernel through the approximation of the marginal distribution using the unlabeled samples. The good performance of the proposed method is illustrated in a hyperspectral image target detection application for thermal hot spot detection. An improvement is observed with respect to the linear and the non-linear kernel-based OSP, demonstrating good generalization capabilities when low number of labeled samples are available, which is usually the case in target detection problems.

引用

页码：566 / +

页数：2

共 16 条

[1]

[Anonymous], 2004, KERNEL METHODS PATTE

[2]

[Anonymous], 2006, IEEE T NEURAL NETWOR

[3]

[Anonymous], 2008, COMPUT SCI

[4]

[Anonymous], 1997, CBMS REGIONAL C SERI

[5] Improved manifold coordinate representations of large-scale hyperspectral scenes [J].

Bachmann, Charles M. ;

Ainsworth, Thomas L. ;

Fusina, Robert A. .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2006, 44 (10) :2786-2803

[6] Exploiting manifold geometry in hyperspectral imagery [J].

Bachmann, CM ;

Ainsworth, TL ;

Fusina, RA .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2005, 43 (03) :441-454

[7] Semi-supervised graph-based hyperspectral image classification [J].

Camps-Valls, Gustavo ;

Bandos, Tatyana V. ;

Zhou, Dengyong .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2007, 45 (10) :3044-3054

[8]

CAMPSVALLS G, 2008, IEEE INT GEOSC REM S

[9] HYPERSPECTRAL IMAGE CLASSIFICATION AND DIMENSIONALITY REDUCTION - AN ORTHOGONAL SUBSPACE PROJECTION APPROACH [J].

HARSANYI, JC ;

CHANG, CI .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1994, 32 (04) :779-785

[10] Kernel orthogonal subspace projection for hyperspectral signal classification [J].

Kwon, H ;

Nasrabadi, NM .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2005, 43 (12) :2952-2962

← 1 2 →