基于神经网络模型技术的南京市主城区城市森林遥感调查

doi:10.11821/yj2006030012

地理研究 ›› 2006, Vol. 25 ›› Issue (3): 468-476.doi: 10.11821/yj2006030012

基于神经网络模型技术的南京市主城区城市森林遥感调查

赵清¹, 郑国强², 黄巧华¹

1. 徐州师范大学城市与环境学院徐州221116;
2. 山东建筑工程学院遥感与GIS实验室,济南250101

收稿日期:2005-10-25 修回日期:2006-03-02 出版日期:2006-06-15 发布日期:2006-06-15
作者简介:赵清(1965-),男,江苏盐城人,博士,副教授。主要从事景观生态与自然资源利用研究。 E-mail:zhaoqingl@163.com
基金资助:
江苏省教育厅高校哲学社会科学基金项目(SWC0531);徐州师范大学自然科学研究基金重点项目(05XLA13)资助

Urban forest remote sensing investigation based on neural network model technology in the main city of Nanjing

ZHAO Qing¹, ZHENG Guo-qiang², HUANG Qiao-hua¹

1. College of Urban and Environmental Sciences,Xuzhou Normal University,Xuzhou 221116,China;
2. Laboratory of RS and GIS,Shandong University of Architcture and Engineering,Jinan 250101,Chian

Received:2005-10-25 Revised:2006-03-02 Online:2006-06-15 Published:2006-06-15

摘要/Abstract

摘要：

城市森林调查是城市森林研究和规划建设的前提和基础工作,而遥感和GIS技术已成为现代城市森林调查的主要方法。遥感信息源和遥感分类技术是决定城市森林遥感调查质量的两个关键因素,研究认为,根据城市森林特点及城市森林研究和规划建设的要求,城市森林遥感调查采用的遥感影像分辨率以8¹0m为宜,神经网络模型分类技术应用于城市森林遥感调查效果较好。本文以南京市主城区为例,以10m分辨率多光谱spot卫星图像与2.5m分辨率全色spot卫星图像的融合图像作为解译信息源,采用dARTMAP神经网络模型进行监督分类,提取了一套具有较高精度的南京市主城区城市森林空间属性数据和图件,并在此基础上分析了南京市城市森林基本特点及规划建设方向。

关键词: 城市森林, 遥感调查, 神经网络模型, 南京市主城区

Abstract:

Urban forest generally refers to the trees and related vegetations in the urban area and its surroundings.Academically established concept of urban forest marks the great change of man's opinion on forest.The urban forest concept was introduced into China in the late（1980s.） Theoretical research on and case study of urban forest becomes more and more popular. Urban forest is a rising research area.Cultivation of urban forest has been an important part in urban planning and sustainable development.Continuous development of remote sensing and GIS facilitates more rapidly and accurately urban forest investigation.Information sources and methods for remote sensing classification are two crucial factors in terms of the quality of urban forest remote sensing investigation. Researches reveal that urban forest is highly fragmentized with a number of patches of different sizes and complex boundaries,hence remote sensing images of relatively high resolution of 8¹0 m are needed.It is difficult to make urban forest remote sensing classification by traditional visual interpretation.Remote sensing classification based on neural network model can well solve such problems as uncertainty of complex boundaries and mixed pixel resolution,much suitable to urban forest remote sensing investigation. Taking the recent high-resolution remote sensing images of Nanjing city as an information source,we have made remote sensing survey of forest landscape in the main part of Nanjing city by use of dARTMAP classification method.Image interpretation is made under Matlab environment and supervised classification is made by use of dARTMAP neural network model.The accuracy analysis function of ERDAS software is employed to make accuracy evaluation of classified data.According to the accurate test confusion matrix,the total classification accuracy reaches 89.0% and kappa coefficient is up to 0.7271.And the forest landscape distribution map of the main city of Nanjing is made and the spatial attribute data of the patches deduced under Arcmap environment.

Key words: urban forest, remote sensing investigation, neural network model, the main city of Nanjing

赵清, 郑国强, 黄巧华. 基于神经网络模型技术的南京市主城区城市森林遥感调查[J]. 地理研究, 2006, 25(3): 468-476.

ZHAO Qing, ZHENG Guo-qiang, HUANG Qiao-hua. Urban forest remote sensing investigation based on neural network model technology in the main city of Nanjing[J]. GEOGRAPHICAL RESEARCH, 2006, 25(3): 468-476.

参考文献

[1] G rey G W,Denek e F J U rban Forest ry N ew Y ork:J oh n W iley&S on s,In c 1978

[2] R ow ant re R A Ecology of U rban For est:Int roduct ion t o Part 1 U rban Ecology,1984,1~1.

[3] M iller R W U rban Forest ry N ew Jersey:Pretice Hall,Engl ew ood Cl iff s,07632,1988

[4] 彭镇华中国城市森林北京:中国林业出版社,2003

[5] 孙冰,粟娟,谢左章城市林业的研究现状与前景南京林业大学学报,1997,21(2):83~88

[6] 白秀萍日本城市森林发展的研究北京:中国林业出版社,1993

[7] 高发全美国城市林业未来的研究方向与重点世界林业动态,2003,(21):4~7

[8] 蒋有绪城市林业的发展趋势与特点世界科技研究与发展,2000,22(5):16~18

[9] 朱文泉,何兴元,陈玮城市森林研究进展生态学杂志,2001,20(5):55~59

[10] 王成,蔡春菊,陶康华城市森林的概念、范围及其研究世界林业研究,2004,17(2):55~6.

[11] 刘纪远,庄大方,凌杨荣基于GIS的中国东北植被分类研究遥感学报1990,2(4):285~29.

[12] 李俊祥,宋永昌浙江天童国家森林公园景观的遥感分类与制图生态学杂志,2003,22(4):102~105

[13] 杨存建,刘纪远,黄河,等热带森林植被生物量与遥感地学数据之间的相关性分析地理研究,2005,24(3):473~479

[14] 孙玉军,王雪军,张志,等基于G IS的森林景观定量分类生态学报,2003,23(12):2540~2544

[15] 车生泉,宋永昌城市绿地景观卫星遥感信息解译城市环境与城市生态,2001,14(2):10~12

[16] 王耀南智能控制系统%%%模糊控制&专家系统&神经网络控制长沙:湖南大学出版社,1996

[17] Wilk inson G G A review of cu rrent is sues in t he in t egrati on of G IS and remot e sensing dat a In t Geograp hical Inf ormati on Sys t ems,1996,62(5):491~499

[18] G rossb erg S A dapt ive pat t ern cl as sifi cat ion and u nivers al record II:Feedback,ex pect at ion,olf act ion,and il lusi on s Biol og,1976,23:187~202

[19] C arpent er G A,Borian a L Dist rib ut ed A R T M A P:a neural net w or k f or f as t dist ribu te s upervis ed leaning N euralN et w or k,1998,11:791~813

[20] 赵清,丁登山,阎传海南京幕燕山地森林植被恢复重建研究地理研究,2003,22(6):742~750

[21] 朱光良浙江省海宁市TM图像土地利用自动分类精度评价方法的试验研究遥感学报,1999,3(2):144~150

[22] 吴健,杨星卫遥感数据分类结果的精度分析遥感技术与应用,1995,10(1):17~24

[23] Forman R T T Lan dscape M osaics:T he Ecol ogy of Landscape and Region Cambrige U n iversit y Pres s,.995

基于神经网络模型技术的南京市主城区城市森林遥感调查

Urban forest remote sensing investigation based on neural network model technology in the main city of Nanjing

赞

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

Metrics

本文评价

推荐阅读 0