全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于FuzzyARTMAP神经网络的高分辨率图象土地覆盖分类及其评价

DOI: 10.11834/jig.20030262

Keywords: 计算机图象处理,Fuzzy,ARTMAP,神经网络,遥感,土地覆盖分类

Full-Text   Cite this paper   Add to My Lib

Abstract:

主要讨论了基于FuzzyARTMAP神经网络的高分辨率遥感图象土地覆盖分类方法及其实践.首先介绍了FuzzyARTMAP神经网络的原理,然后用SPOTXS图象试验数据进行土地覆盖分类.分类结果与传统的最大似然监督分类(MLC)、反馈式(BackPropagation,BP)神经网络的分类结果进行了比较.通过抽取500个样点对3种分类结果进行精度评价表明,FuzzyARTMAP神经网络相对其他两种方法,分类精度均有不同程度的改善,具有更好的分类结果,总分类精度比MLC和BP算法分别提高17.41%、7.32%.最后,对不同分类方法对于土地覆盖分类结果的影响进行了评价和分析.试验表明,FuzzyARTMAP神经网络用于高分辨图象土地覆盖分类研究可以获得相对较好的分类结果.

References

[1]  [1]Carpenter G A, Gjiaja M N, Gopal S et al. ART neural networks for remote sensing: Vegetation classification from Landsat TM and terrain data[J]. IEEE Trans. Geosci. Remote Sens. , 1997, 35(2): 308~325.
[2]  [3]Carpenter G A, Grossberg S, Reynolds J H. ARTMAP:Supervised real-time learning and classification of nonstationary data by a self organizing neural network[J]. Neural Networks,1991, 4(5): 565~588.
[3]  [5]Gopal S, Woodcock C E, Strahler A H. Fuzzy neural network classification of global land cover from a 1° AVHRR data set[J].RemoteSens. of Environ., 1999, 67(2): 230~243.
[4]  [7]周志华等.自适应谐振理论综述[J].计算机科学.1999,26(4):54~56.
[5]  [2]Carpenter G A, Grossberg S, Rosen D B. Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system[J]. Neural Networks, 1991, 4(6):759~771.
[6]  [4]Bartfi G. An improved learning algorithm for the Fuzzy ARTMAP neural network[A]. In:Proceedings of The Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems [C], Duneding, New Iealand, IEEE Computer Society Press. 1995: 34~37.
[7]  [6]杨建刚.人工神经网络实用教程[M].杭州:浙江大学出版社,2001:114~122.
[8]  [8]阎平凡,张长水.人工神经网络与模拟进化计算[M].北京:清华大学出版社,2000:185~189.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133