Comparison of non-linear mixture models: Sub-pixel classification

被引：90
作者：
Liu, WG
Wu, EY
机构：
[1] ACI Worldwide Inc, Riverside, RI 02915 USA
[2] Med Univ S Carolina, Charleston, SC 29425 USA
来源：
REMOTE SENSING OF ENVIRONMENT | 2005年 / 94卷 / 02期
基金：
美国国家科学基金会;
关键词：
mixture model; sub-pixel classification; non-linear; neural network; MLP; ARTMAP; ART-MMAP; regression tree;
D O I：
10.1016/j.rse.2004.09.004
中图分类号：
X [环境科学、安全科学];
学科分类号：
08 ; 0830 ;
摘要：
Sub-pixel level classification is essential for the successful description of many land cover patterns with spatial resolution of less than similar to1 km and has been widely used in global or continental scale land cover mapping with remote sensing data. This paper presents a general comparison of four non-linear models for sub-pixel classification: ARTMAP. ART-MMAP. Regression Tree (RT) and Multilayer Perceptron (MLP) with Back-Propagation (BP) algorithm. The comparison is based oil four factors: accuracy. model complexity, interpolation ability and error distribution. Two data sets, one simulated and one real world MODIS satellite image. were used to demonstrate the characteristics of each model. Experimental results show the superior performance of MLP with the simulated data set and better performance of ART-MMAP with the MODIS data set. (C) 2004 Elsevier Inc. All rights reserved.
引用
收藏
页码：145 / 154
页数：10
相关论文
共 27 条
[11]   Non-linear mixture modelling without end-members using an artificial neural network [J].
Foody, GM ;
Lucas, RM ;
Curran, PJ ;
Honzak, M .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 1997, 18 (04) :937-953
[12]   Approaches for the production and evaluation of fuzzy land cover classifications from remotely-sensed data [J].
Foody, GM .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 1996, 17 (07) :1317-1340
[13]   Sharpening fuzzy classification output to refine the representation of sub-pixel land cover distribution [J].
Foody, GM .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 1998, 19 (13) :2593-2599
[14]  
FOODY GM, 1992, PHOTOGRAMM ENG REM S, V58, P1335
[15]   μARTMAP:: Use of mutual information for category reduction in Fuzzy ARTMAP [J].
Gómez-Sánchez, E ;
Dimitriadis, YA ;
Cano-Izquierdo, JM ;
López-Coronado, J .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2002, 13 (01) :58-69
[16]   Gaussian mixture discriminant analysis and sub-pixel land cover characterization in remote sensing [J].
Ju, JC ;
Kolaczyk, ED ;
Gopal, S .
REMOTE SENSING OF ENVIRONMENT, 2003, 84 (04) :550-560
[17]  
LIU W, 2001, 4 INT C INF FUS MONT
[18]  
LIU W, 2001, DATA MINING SCI ENG, P205
[19]   ART-MMAP: A neural network approach to subpixel classification [J].
Liu, WG ;
Seto, KC ;
Wu, EY ;
Gopal, S ;
Woodcock, CE .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2004, 42 (09) :1976-1983
[20]  
MCIVER D, 2001, THESIS BOSTON U
123