Image Classification Method in Landuse Dynamic Detection Based on Mult-i source Remote Sensing Data—A Case Study in the Loess Plateau of Northern Shaanxi Province

LIU Yongmei; LI Rui; YANG Qinke

您当前的位置：

首页 >

文章列表页 >

Image Classification Method in Landuse Dynamic Detection Based on Mult-i source Remote Sensing Data—A Case Study in the Loess Plateau of Northern Shaanxi Province

- Image Classification Method in Landuse Dynamic Detection Based on Mult-i source Remote Sensing Data—A Case Study in the Loess Plateau of Northern Shaanxi Province
- Bulletin of Soiland Water Conservation Vol. 25, Issue 6, Pages: 63-66(2006)
- 作者机构：
  
  1. 西北大学城市与资源学系,陕西,西安,710069
  2. 中国科学院水利部水土保持研究所, 陕西杨凌,712100
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2006
- 稿件说明：
移动端阅览
LIU Yongmei, LI Rui, YANG Qinke. Image Classification Method in Landuse Dynamic Detection Based on Mult-i source Remote Sensing Data—A Case Study in the Loess Plateau of Northern Shaanxi Province[J]. Bulletin of Soiland Water Conservation, 2006, 25(6): 63-66.
DOI：

LIU Yongmei, LI Rui, YANG Qinke. Image Classification Method in Landuse Dynamic Detection Based on Mult-i source Remote Sensing Data—A Case Study in the Loess Plateau of Northern Shaanxi Province[J]. Bulletin of Soiland Water Conservation, 2006, 25(6): 63-66. DOI：

摘要

在陕北黄土丘陵沟壑区的土地利用动态监测中

采用一种遥感影像和单纯的监督分类方法

难以获得高精度的土地利用数据。为解决此问题

以陕北无定河流域为研究区

以主成分变换的方法对多源遥感影像(TM多光谱数据和SPOT全色波段数据)进行融合处理;同时在分类中采用监督分类与非监督分类相结合的混合分类法

改进训练样本选取方法。先以非监督分类获得初始训练样本

在对样本进行删除、增补、合并等调整的基础上

再进行监督分类

这2种方法的结合使用

使土地利用信息自动提取的精度明显提高。与仅以TM影像为信息源

采用单纯监督分类法的分类结果对比可知

土地利用各类别的提取精度都有不同程度的提高

分类总精度从82.0%提高到89.2%;水体、水田和城镇用地等面积较小类别的精度提高了10%以上;坡耕地与林草地的混分现象明显减少

精度均提高了5%以上

取得了良好的分类效果。研究结果为陕北黄土丘陵沟壑区土地利用变化的动态监测

提供了重要的技术支持和借鉴。

Abstract

The landuse classification accuracy based on single remotely sensed data and simple supervised classification is unsatisfactory to the landuse investigation in loess hill and gully area. By taking the Wuding River watershed in Northern Shaanxi Province as a test area

the TM mult-i spectral data and SPOT pan data were merged by the method of Principal Components Analysis. Based on the merged image

the landuse categories were then extracted by applying an integration of supervised classification and unsupervised classification. The combination of two methods remarkably improved sampling method. Compared to the classification based on the single TM mult-ispectral data and supervised classif icat ion

the total accuracy increased from 82.0% to 89.2%

especially the accuracy of city and town area

paddy field

water area increased over 10%

the mixture of sloping land and forest (grassland)decreased remarkably

and the accuracy of the two categories increased over 5%. The result is of critical significance in landuse dynamic monitoring in the area.

关键词

Keywords

references

Views

1696

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Land-use and Cover Change of Coarse Sand Area in Middle Reaches of Yellow River

A Preliminary Study on Construction of Land Use Database at County Level

Classifications of Eco-economic Typies on Karst Areas in Guizhou Province

Dynamic Landscape Pattern of Land Use and Soil and Water Loss in the Ertan Reservoir Area of Yanbian County

Variability and Potential Impact Factors of Inflows into the Miyun Reservoir

Related Author

LIANG Wei

YANG Qin-ke

ZHAO Mi-jin

CUI Xiao-lin

CHEN Tao

XU Yao

TU Dai-lun

ZHANG Xin-hai

Related Institution

Institute of Soil and Water Conservation, CAS and MWR, Yangling District

Department of Survey Engineering, Xi’an University of Science and Technology

Institute of Land and Resources, China West Normal University, Nanchong

Chengdu University of Technology

Sichuan Academy of Forestry

⁰