基于变化检测的滑坡灾害自动识别

英文篇名：Automatic Recognition of Landslides Based on Change Detection
中文刊名：遥感信息
英文刊名：Remote Sensing Information
作者：李松 ; 李亦秋 ; 安裕伦
英文作者：LI Song① ; ② ; LI Yiqiu③ ; ④ ; AN YU-Lun②(① State Key Laboratory of Remote Sensing Science ; Institute of Remote Sensing Applications ; Chinese Academy of Sciences ; Beijing 100101 ; ② School of Geographical and Environmental Sciences Guizhou Normal University ; Guiyang Guizhou 552100 ; ③ Institute of GIS ; RS & GPS ; Beijing Forestry University ; Beijing 100083 ; ④Department of Resource and Environmental Sciences Mian Yang Normal University ; Mianyang 621000)
中文关键词：变化检测 ; 多时相 ; 遥感影像 ; 滑坡灾害 ; 信息识别
英文关键词：change detection ; multi-temporal ; imagery ; landslide disasters ; information identification
出版日期：2010-02-15
机构：中国科学院遥感应用研究所遥感科学国家重点实验室;贵州师范大学地理与环境科学学院;北京林业大学测绘与3S技术中心;绵阳师范学院资源环境科学系;
年：2010
期：01
出版单位：遥感信息

摘要

在分析当前滑坡灾害信息识别方法的基础上,指出这些方法的适用性和不足之处,并针对这些不足之处,以滑坡的地学原理为依据,提出了以多时相遥感影像为数据源,结合纹理分析的变化检测自动识别滑坡灾害信息的方法。最后,以地震前(2006-5-14)后(2008-6-3)的北川县城及附近区域的福卫2号多光谱遥感影像作为数据源,以结合比率变换和纹理分析的变化检测进行滑坡灾害信息识别试验。结果表明,结合纹理分析的变化检测方法能够突破影像光谱特征的局限,对于滑坡灾害信息识别具有显著的适用性。
The current recognition approaches of landslide disasters mostly are based on visual interpretation,which may result in low productivity.This paper analyzes the current identification methods of the landslide disasters,and their applicability.According to the disadvantages and principles of landslide disasters,we bring forward a more effective approach to identify landslides,which uses change detection combined with texture analysis in multi-temporal images.Additionally,this paper takes Beichuan county which has been affected by the great earthquake seriously as a case to implement the new method in application of landslide automatic identification,and takes multi-temporal ROCSAT-2 as the data resources of pre-landslide and post-landslide study respectively.The finding shows that the method combined with change detection can use the more image information including texture,and it is available to the automatic recognition of landslide disasters.

引文

1王坚.滑坡灾害遥感遥测预警理论及方法[D].南京:中国矿业大学博士学位论文,2006.
    2付文杰,洪金益.基于支持向量机的滑坡灾害信息遥感图像提取研究[J].水土保持研究,2006,13(4):120～122.
    3叶润青,邓清禄,王海庆.基于图像分类方法滑坡识别与特征提取———以归州老城滑坡为例[J].工程地球物理学报,2007,4(6):475～477.
    4Wen-Tzu Lin,Wen-Chieh Chou,Chao-Yuan Lin,et al.Vegetation recovery monitoring and assessment at landslides caused by earthquake in Central Tai wan[J].Forest Ecology and Management,2005(210):55～66.
    5Javier Hervas,Jose I.Barredo,Paul L.Rosin,et al.Monitoringlandslides fromoptical remotely sensedi magery:the case his-tory of Tessina landslide,Italy[J].Geomorphology,2003(54):63～75.
    6Ashbindu Singh.Digital change detection techniques using remotely-sensed data[J].International Journal of Remote Sens-ing,1989(10):989.
    7D.Lu,P.Musel,E.Brondizio,et al.Change detection techniques[J].I mage Processing,2005,14(3):294～307.
    8李德仁.利用遥感影像进行变化检测[J].武汉大学学报.信息科学版,2003,8(特刊):7～12.
    9Gopal S,Woodcock C.Remote sensing of forest change using artificial neural networks[J].IEEE Transactions on Geoscience and Remote Sensing,1996(34):398.
    10D.W.J.Stein,S.J.Beaven,L.E.Hoff,et al,.A nomaly detection from hyperspectral i magery[J].IEEE Signal Preocesss.Mag.,2002,19(1):58～69.
    11陈述彭(主编).遥感大辞典[M].北京:科学出版社,1990:339.
    12W.M.D..A prehistoric landslide in the alps[J].Science,1907,26(657):153～154.