分层神经网络分类算法

被引：21

作者：

熊桢

郑兰芬

童庆禧

机构：

[1] 中国科学院遥感信息科学开放研究实验室!北京

来源：

测绘学报 | 2000年 / 03期

关键词：

分层处理; 神经网络; 遥感图像分类; 分类精度;

D O I：

暂无

中图分类号：

P237 [测绘遥感技术];

学科分类号：

1404 ;

摘要：

提高遥感图像分类精度一直是受到普遍关注的焦点问题。近年来 ,人工神经网络技术和分层处理技术由于它们的许多优点受到广泛欢迎。本文把这两种技术结合起来 ,提出了分层神经网络的概念 ,并基于此设计了一种分层神经网络分类算法。通过与最大似然法的对比实验表明 ,这种分层神经网络分类算法可以明显地提高分类精度 ,并对不规则分布的复杂数据具有很强的处理能力。

引用

页码：229 / 234

页数：6

共 9 条

[1] The Effect of Neural -Network Structure on a Multispectral Land-Use LandCover Classification. JUSTIN D,et al. Photogrammetric Engineering &Remote Sensing . 1997
[2] Hierachical Maximum-Likelihood Classification for Improved Accuracies. JAYANTHA E. IEEE Transactions on Geoscience and Remote Sensing . 1997
[3] A Fast Two-Stage Classification Method for High-Dimensional Remote Sensing Data. TU Te-ming,CHEN Chin-hsing,WU Jiunn-lin,et al. IEEE Transactions on Geoscience and Remote Sensing . 1998
[4] A Detailed Comparison of Backpropagation Neural Network and MaximumLikelihood Classifiers for Urban Land Use Classification. JUSTIN D,et al. IEEE Transactions on Geoscience and Remote Sensing . 1995
[5] A Neural Network Model for Estimating Sea Surface Chlorophyll and Sediments from Thematic Mapper Imagery. LOUIS E,KEINER,YAN Xiao-hai. Remote Sensing of Environment . 1998
[6] Classification Trees: An Alternative to Traditional Land Cover Classifiers. HANSEN M,DUBAYAN R,DEFRIES R. International Journal of Remote Sensing . 1996
[7] Multisource Classification of Complex Rural Areas by Statistical and Neural -Network Approaches. BRUZZONE L,CONESE C,MASELLI F,et al. Photogrammetric Record . 1997
[8] Neural Network Approach to Land Cover Mapping. TOMOJI Y,SIGERU O. IEEE Transactions on Geoscience and Remote Sensing . 1994
[9] A Hybrid Histogram Neural Network Classifier for Creating Global Cloud Masks. LOGAR A,CORWIN E,ALEXANDER J,et al. International Journal of Remote Sensing . 1997

← 1 →