Improving the performance of classifiers in high-dimensional remote sensing applications: An adaptive resampling strategy for error-prone exemplars (ARESEPE)

被引:17
作者
Bachmann, CM [1 ]
机构
[1] USN, Res Lab, Remote Sensing Div, Washington, DC 20375 USA
来源
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING | 2003年 / 41卷 / 09期
关键词
active learning; active sampling; barrier islands; hyperspectral; land-cover classification; Virginia Coast Reserve;
D O I
10.1109/TGRS.2003.817207
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
In the past, "active learning" strategies have been proposed for improving the convergence and accuracy of statistical classifiers. However, many of these approaches have large storage requirements or unnecessarily large computational burdens and, therefore, have been impractical for the large-scale databases typically found in remote sensing, especially hyperspectral applications. In this paper, we develop a practical on-line approach with only modest storage requirements. The new approach improves the convergence rate associated with the optimization of adaptive classifiers, especially in high-dimensional remote sensing data. We demonstrate the new approach using PROBE2 hyperspectral imagery and find convergence time improvements of two orders of magnitude in the optimization of land-cover classifiers.
引用
收藏
页码:2101 / 2112
页数:12
相关论文
共 15 条
[1]   Automatic classification of land cover on Smith Island, VA, using HyMAP imagery [J].
Bachmann, CM ;
Donato, TF ;
Lamela, GM ;
Rhea, WJ ;
Bettenhausen, MH ;
Fusina, RA ;
Du Bois, KR ;
Porter, JH ;
Truitt, BR .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2002, 40 (10) :2313-2330
[2]  
BACHMANN CM, IN PRESS IEEE T GEOS
[3]  
BACHMANN CM, 2002, P IGARSS TOR ON CAN
[4]  
Boardman J.W., 1998, SUMM 7 JPL AIRBORNE, V97, P21
[5]   The significance of border training patterns in classification by a feedforward neural network using back propagation learning [J].
Foody, GM .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 1999, 20 (18) :3549-3562
[6]   Statistical active learning in multilayer perceptrons [J].
Fukumizu, K .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2000, 11 (01) :17-26
[7]   Development of a line-by-line-based atmosphere removal algorithm for airborne and spaceborne imaging spectrometers [J].
Gao, BC ;
Davis, CO .
IMAGING SPECTROMETRY III, 1997, 3118 :132-141
[8]   QUERY-BASED LEARNING APPLIED TO PARTIALLY TRAINED MULTILAYER PERCEPTRONS [J].
HWANG, JN ;
CHOI, JJ ;
OH, S ;
MARKS, RJ .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1991, 2 (01) :131-136
[9]   DISCRIMINATIVE LEARNING FOR MINIMUM ERROR CLASSIFICATION [J].
JUANG, BH ;
KATAGIRI, S .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1992, 40 (12) :3043-3054
[10]  
Kohonen T., 1997, Self-organizing Maps, V2nd ed.