[1]林 熙,罗小军*,郭红梅,等.基于语义约束的GF-1遥感影像山区居民地提取方法[J].山地学报,2017,(01):102-111.[doi:10.16089/j.cnki.1008-2786.000201]
　LIN Xi,LUO Xiaojun,GUO Hongmei,et al.Extraction of Residential areas in Mountainous Areas from GF-1 Remote Sensing Image by Semantic Constraints[J].Mountain Research,2017,(01):102-111.[doi:10.16089/j.cnki.1008-2786.000201]
点击复制

基于语义约束的GF-1遥感影像山区居民地提取方法()
分享到：

《山地学报》[ISSN:1008-2186/CN:51-1516]

卷:
期数:
2017年01期
页码:
102-111
栏目:
山地技术
出版日期:
2017-01-30

文章信息/Info

Title:
Extraction of Residential areas in Mountainous Areas from GF-1 Remote Sensing Image by Semantic Constraints
文章编号:
1108-2786-(2017)1-102-10
作者:
林 熙1; 2; 罗小军1*; 郭红梅3; 刘国祥1; 张帅娟1; 陈 银1
1.西南交通大学 地球科学与环境工程学院,四川 成都 610031;
2 重庆市地理信息中心,重庆 401121;
3 四川省地震局,四川 成都 610041
Author(s):
LIN Xi1;  LUO Xiaojun1;  GUO Hongmei2;  LIU Guoxiang1;  ZHANG Shuaijuan1;  CHEN Yin1
1. Faculty of Geosciences and Environmental Engineering, Southwest Jiaotong University, Chengdu, Sichuan 611756, China;
2. Chongqing Geomatics Center, Chongqing 401121, China;
3. Sichuan Earthquake Administration, Chengdu, Sichuan 610041, China
关键词:
高分一号; 面向对象; 语义约束; 山区; 居民地; 信息提取
Keywords:
GF-1;  object-oriented;  semantic constraint;  residential area;  mountainous area;  information extraction
DOI:
10.16089/j.cnki.1008-2786.000201
文献标志码:
A
摘要:
山区居民地空间分布信息是山区灾害应急响应与评估的重要基础资料。我国大力发展的高分辨遥感系统,为快速获取山区居民地空间分布信息提供了数据保障,对灾害应急与评估具有重要的现实意义。针对高分辨率遥感影像居民地提取结果误分对象较多的情况,本文提出一种基于语义约束的高分一号(GF-1)遥感影像山区居民地提取方法,其基本思路是:根据山区居民地独特的分布规律,制定山谷线、山坡、雪线等语义约束条件,并将其与面向对象方法相结合进行居民地提取。以覆盖四川省康定县的一景GF-1影像为例进行实验,采取语义约束下的山区居民地提取,正确率为82.91%,漏分率仅为7.86%。与不使用语义约束的面向对象分类法直接提取结果相比,正确率提高了1.2倍。实验表明,本文提出的山区居民地提取方法能够有效改善山区居区地信息提取效果。
Abstract:
The development of high-resolution remote sensing system in China provides a way to extract accurate spatial distribution of residential areas, which is very important for emergency response and assessment for disaster in the mountain areas. However, there is always unavoidable misclassification during the residential areas, when they are extracted from high-resolution remote sensing images. In order to improve accuracy of residential areas extraction, a new method based on semantic constraints was proposed in this paper. Three semantic constraints were established according to the distribution characteristics of residential areas i.e., valley line, slope, and snow-covering conditions. The object-oriented method was used under these semantic constraints. In this paper, a mountain area(1000 km2)in Kangding county, Sichuan was selected as case study. The results showed that ratio of correct extraction was 82.91% by the proposed method, and ratio of miss extraction was only 7.86%. The correct extraction ratio was increased by 1.2 times as compared with that of the conventional object-oriented method. The results of case study indicated that this method could effectively improve extraction accuracy of residential areas in mountainous areas.

参考文献/References:

[1] CHEN Ningsheng, YANG Chenglin, ZHOU Wei, et al. The critical rainfall characteristics for torrents and debris flow in the WenChuan earthquake stricken area [J]. Journal of Mountain Science, 2009, 6(4): 362-372
[2] CHEN Ningsheng, LU Yang, ZHOU Haibo, et al. Combined impacts of antecedent earthquakes and droughts on hazardous debris flows[J]. Journal of Mountain Science, 2014,11(6):1507-1520
[3] IRMLER R, DAUT G, MÄUSBACHER R. A debris flow calendar derived from sediments of lake Lago di Braies(N. Italy)[J]. Geomorphology, 2006, 77(1): 69-78

相似文献/References:

[1]鲁恒,李永树,唐敏,等.面向对象的山地区域多源遥感影像分割尺度选择及评价[J].山地学报,2011,(06):688.
　LU Heng,LI Yongshu,TANG Min.Evaluation and Selection of Segmentation Scale with Objectoriented Method in Multiple Source Remote Sensing Image of Mountain Areas[J].Mountain Research,2011,(01):688.
[2]朱俊凤,钱峻屏,廖广社,等.基于对象方法的南岭山区雨雪冰冻灾害遥感检测与空间分析[J].山地学报,2010,(04):478.

备注/Memo

备注/Memo:
基金项目(Foundation item):高分光学遥感应急救援示范应用(31-Y30B09-9001-13/15-15); 国家自然科学基金项目(41271448, 41474003); 973课题(2012CB719901); 西南交通大学研究生创新实验实践项目(YC201514103)[Emergency Rescue Demonstration Application Based on High Resolution Optical Remote Sensing(31-Y30B09-9001-13/15-15); National Natural Science Foundation of China(41271448, 41474003); 973 Program(2012CB719901); Graduates' Innovative Experimental Practice Items of Southwest Jiaotong University(YC201514103)]
作者简介(Biography):林熙(1989-),男,四川绵阳人,硕士研究生,研究方向为遥感应用研究 [Lin Xi(1989-), male, Sichuan, M.Sc. candidate, research on application of remote sensing] E-mail: linxieryu@outlook.com
*通信作者(Corresponding author):罗小军(1974-),男,四川安岳人,博士,副教授,主要从事摄影测量与遥感、InSAR理论及应用研究[Luo Xiaojun(1974-), male, Sichuan, Ph. D, associate professor, research on the theory and application of interferometric synthetic aperture radar(InSAR), and the processing and information abstraction of optical remote sensing images] E-mail: lxj@swjtu.cn
更新日期/Last Update: 2017-01-30