Unsupervised retraining of a maximum likelihood classifier for the analysis of multitemporal remote sensing images

被引：181

作者：

Bruzzone, L ^{[1
]}

Prieto, DF ^{[1
]}

机构：

[1] Univ Trent, Dept Civil & Environm Engn, Trento, Italy

来源：

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING | 2001年 / 39卷 / 02期

关键词：

expectation maximization algorithm; land-cover map updating; maximum likelihood (ML) classification; remote sensing; unsupervised retraining;

D O I：

10.1109/36.905255

中图分类号：

P3 [地球物理学]; P59 [地球化学];

学科分类号：

0708 ; 070902 ;

摘要：

An unsupervised retraining technique for a maximum likelihood (ML) classifier is presented. The proposed technique allows the classifier's parameters, obtained by supervised learning on a specific image, to be updated in a totally unsupervised way on the basis of the distribution of a new image to be classified. This enables the classifier to provide a high accuracy for the new image even when the corresponding training set is not available.

引用

收藏

页码：456 / 460

页数：5

相关论文

共 16 条

[1] NEURAL NETWORK APPROACHES VERSUS STATISTICAL-METHODS IN CLASSIFICATION OF MULTISOURCE REMOTE-SENSING DATA [J].

BENEDIKTSSON, JA ;

SWAIN, PH ;

ERSOY, OK .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1990, 28 (04) :540-552

[2] An extension of the Jeffreys-Matusita distance to multiclass cases for feature selection [J].

Bruzzone, L ;

Roli, F ;

Serpico, SB .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1995, 33 (06) :1318-1321

[3] A technique for the selection of kernel-function parameters in RBF neural networks for classification of remote-sensing images [J].

Bruzzone, L ;

Prieto, DF .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1999, 37 (02) :1179-1184

[4] An approach to feature selection and classification of remote sensing images based on the Bayes rule for minimum cost [J].

Bruzzone, L .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2000, 38 (01) :429-438

[5] A neural-statistical approach to multitemporal and multisource remote-sensing image classification [J].

Bruzzone, L ;

Prieto, DF ;

Serpico, SB .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1999, 37 (03) :1350-1359

[6]

Chavez P. S, 1994, PHOTOGRAMM ENG REMOT, V60, P1285

[7]

CHAVEZ PS, 1989, PHOTOGRAMM ENG REM S, V55, P1285

[8] MAXIMUM LIKELIHOOD FROM INCOMPLETE DATA VIA EM ALGORITHM [J].

DEMPSTER, AP ;

LAIRD, NM ;

RUBIN, DB .

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-METHODOLOGICAL, 1977, 39 (01) :1-38

[9] Maximizing land cover classification accuracies produced by decision trees at continental to global scales [J].

Friedl, MA ;

Brodley, CE ;

Strahler, AH .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1999, 37 (02) :969-977

[10] Mediterranean vegetation analysis by multi-temporal satellite sensor data [J].

Grignetti, A ;

Salvatori, R ;

Casacchia, R ;

Manes, F .

INTERNATIONAL JOURNAL OF REMOTE SENSING, 1997, 18 (06) :1307-1318