Analysis of Multitemporal Classification Techniques for Forecasting Image Time Series

被引：17

作者：

Flamary, R. ^{[1
]}

Fauvel, M. ^{[2
,3
]}

Mura, M. Dalla ^{[4
]}

Valero, S. ^{[5
]}

机构：

[1] Univ Nice Sophia Antipolis, CNRS, Observ Cote Azur, Lab Lagrange UMR 7293, F-06300 Nice, France

[2] Univ Toulouse, INP, ENSAT, UMR DYNAFOR 1201, F-31326 Castanet Tolosan, France

[3] INRA, UMR DYNAFOR 1201, F-31326 Castanet Tolosan, France

[4] Inst Natl Polytech Grenoble, GIPSA Lab, F-38402 St Martin Dheres, France

[5] CNRS, ISIS, CESBIO, UMR 5126, F-31401 Toulouse, France

来源：

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS | 2015年 / 12卷 / 05期

关键词：

Classification; satellite image time series; transfer learning; VEGETATION INDEX DATA; MODIS;

D O I：

10.1109/LGRS.2014.2368988

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：

The classification of an annual time series by using data from past years is investigated in this letter. Several classification schemes based on data fusion, sparse learning, and semisupervised learning are proposed to address the problem. Numerical experiments are performed on a Moderate Resolution Imaging Spectroradiometer image time series and show that while several approaches have statistically equivalent performances, a support vector machine with l(1) regularization leads to a better interpretation of the results due to their inherent sparsity in the temporal domain.

引用

页码：953 / 957

页数：5

共 21 条

[1]

[Anonymous], 2009, Kernel Methods for Remote Sensing Data Analysis

[2] Forecasting crop yield using remotely sensed vegetation indices and crop phenology metrics [J].

Bolton, Douglas K. ;

Friedl, Mark A. .

AGRICULTURAL AND FOREST METEOROLOGY, 2013, 173 :74-84

[3] Introduction to the Special Issue on Analysis of Multitemporal Remote Sensing Data [J].

Bovolo, Francesca ;

Bruzzone, Lorenzo ;

King, Roger L. .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2013, 51 (04) :1867-1869

[4] Classifying multiyear agricultural land use data from Mato Grosso using time-series MODIS vegetation index data [J].

Brown, J. Christopher ;

Kastens, Jude H. ;

Coutinho, Alexandre Camargo ;

Victoria, Daniel de Castro ;

Bishop, Christopher R. .

REMOTE SENSING OF ENVIRONMENT, 2013, 130 :39-50

[5] 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

[6] Contribution of multispectral and multiternporal information from MODIS images to land cover classification [J].

Carrao, Hugo ;

Goncalves, Paulo ;

Caetano, Mario .

REMOTE SENSING OF ENVIRONMENT, 2008, 112 (03) :986-997

[7]

Chapelle Olivier, 2006, Semi-Supervised Learning, DOI DOI 10.7551/MITPRESS/9780262033589.001.0001

[8] Updating Land-Cover Maps by Classification of Image Time Series: A Novel Change-Detection-Driven Transfer Learning Approach [J].

Demir, Beguem ;

Bovolo, Francesca ;

Bruzzone, Lorenzo .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2013, 51 (01) :300-312

[9] TEMPORAL KERNELS FOR THE IDENTIFICATION OF GRASSLAND MANAGEMENT USING TIME SERIES OF HIGH SPATIAL RESOLUTION SATELLITE IMAGES [J].

Dusseux, Pauline ;

Corpetti, Thomas ;

Hubert-Moy, Laurence .

2013 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2013, :3258-3260

[10] A Combined Support Vector Machines Classification Based on Decision Fusion [J].

Fauvel, Mathieu ;

Chanussot, Jocelyn ;

Benediktsson, Jon Atli .

2006 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, VOLS 1-8, 2006, :2494-+

← 1 2 3 →