A NOVEL APPROACH TO TARGETED LAND-COVER CLASSIFICATION OF REMOTE-SENSING IMAGES

被引：0

作者：

Marconcini, Mattia ^{[1
]}

Fernandez-Prieto, Diego ^{[1
]}

机构：

[1] ESA ESRIN, European Space Agcy, Earth Observat Sci Applicat & Future Technol Dept, I-00044 Rome, Italy

来源：

2012 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS) | 2012年

关键词：

targeted land-cover classification; expectation maximization; Markov random fields;

D O I：

10.1109/IGARSS.2012.6351933

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

In several real-world applications the objective of land-cover classification is actually limited to map one or few specific "targeted" land-cover classes over a certain area. In such cases, ground truth is generally available for the only land-cover classes of interest, which limits (or hinders) the possibility of successfully employing standard supervised approaches that require an exhaustive ground truth for all the land-cover classes characterizing the investigated area. In this paper, we present a novel technique capable of addressing this challenging issue by exploiting the only ground truth available for the only land-cover classes of interest. In particular, the proposed method exploits the expectation-maximization (EM) algorithm and an iterative labeling strategy based on Markov random fields (MRF) accounting for spatial correlation. Experimental results confirmed the effectiveness and the reliability of the proposed technique.

引用

页码：7345 / 7348

页数：4

共 6 条

[1] [Anonymous], 1973, Pattern Classification and Scene Analysis
[2] A technique for the selection of kernel-function parameters in RBF neural networks for classification of remote-sensing images
Bruzzone, L
Prieto, DF
[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1999, 37 (02): : 1179 - 1184
[3] DEMPSTER A, 1977, ROYAL STAT SOC B
[4] Jeon B., 1999, IEEE T GEOSCI REM SE, V37
[5] Solberg A. H. S., 1996, IEEE T GEOSCI REM SE, V34
[6] Tax D. M. J., 2002, One-class classification: Concept-learning in the absence of counter-examples

← 1 →