测绘通报 ›› 2019, Vol. 0 ›› Issue (6): 89-91,95.doi: 10.13474/j.cnki.11-2246.2019.0191

• 技术交流 • 上一篇    下一篇

面向对象的沿海地区土地利用/覆被信息提取研究

杨小艳1,2, 刘文璐1, 李龙2,3, 陈龙乾2, 陈龙高1   

  1. 1. 江苏师范大学地理测绘与城乡规划学院, 江苏 徐州 221116;
    2. 中国矿业大学环境与测绘学院, 江苏 徐州 221116;
    3. Department of Geography, Earth System Science, Vrije Universiteit Brussel, Brussels 1050
  • 收稿日期:2018-09-28 修回日期:2018-11-07 出版日期:2019-06-25 发布日期:2019-07-01
  • 通讯作者: 陈龙高。E-mail:longgao.chen@jsnu.edu.cn E-mail:longgao.chen@jsnu.edu.cn
  • 作者简介:杨小艳(1976-),女,博士,副教授,主要研究方向为土地信息处理与应用。E-mail:yangxy0705@163.com
  • 基金资助:

    国家自然科学基金(41601087;41271121);江苏省大学生创新训练重点项目(201710320029);江苏高校优势学科建设工程项目

Object-oriented land use/cover classification in coastal area

YANG Xiaoyan1,2, LIU Wenlu1, LI Long2,3, CHEN Longqian2, CHEN Longgao1   

  1. 1. School of Geography, Geomatics and Planning, Jiangsu Normal University, Xuzhou 221116, China;
    2. School of Environment and Spatial Informatics, China University of Mining and Technology, Xuzhou 221116, China;
    3. Department of Geography, Earth System Science, Vrije Universiteit Brussel, Brussels 1050, Belgium
  • Received:2018-09-28 Revised:2018-11-07 Online:2019-06-25 Published:2019-07-01

摘要:

土地利用/覆被(LUC)可为土地资源领域相关研究提供基础数据。本文构建了面向对象的LUC分类方法,并以沿海特殊土地类型区连云港市为例,应用Landsat 8影像开展了实证研究。结果表明:①总体分类精度达到85.06%,总体Kappa系数为0.83,超过了0.7的最低允许判别精度;②该方法可以有效地减少研究区因南北部区域耕地植被覆盖度不同导致的错分现象,并可以用于盐田与滩涂信息的提取工作;③该方法既可为研究区土地利用相关研究提供符合精度要求的数据,也可为其他沿海地区进行土地利用/覆被信息提取工作提供参考和借鉴。

关键词: 土地利用/覆被(LUC), 面向对象, 分类规则, 沿海地区, 遥感

Abstract:

Land use/cover (LUC) information is a very essential dataset in supporting the related research and application. To extract the LUC information in the coastal area, an object-oriented based classification method is proposed and applied to Lianyungang city using Landsat 8 imagery. The results indicate that the accuracy of the classification exceeded the minimum allowed discriminant accuracy 0.7 with the overall accuracy 85.06% and the overall Kappa coefficient is 0.83. The methodology can reduce the misclassification of arable land due to the vegetation coverage between the southern plains and northern hills, and can be used to extract the tideland and salt-field in the area. The methodology can provide the LUC data with agreed accuracy for the land related research for Lianyungang city, and support the extraction of LUC information in other similar coastal areas.

Key words: land use/cover (LUC), object-oriented, classification rules, coastal area, remote sensing

中图分类号: