灾害学2017，Vol.32Issue(3)：210-215,6.DOI:10.3969/j.issn.1000-811X.2017.03.035
基于面向对象的高分遥感数据甘肃黑方台黄土滑坡半自动识别
Semiautomatic Object-oriented Loose Landslide Recognition based on High Resolution Remote Sensing Images in Heifangtai, Gansu
摘要
Abstract
Detection of landslide is the foundation of landslide study,is widely applied in landslide investigation and landslide mapping,hazard assessment,etc.Heifangtai in Gansu province was chosen as the study area.Recognition of landslide was conducted on the Geoeye-1 and DEM using object-oriented classification methods.In a first step,the use of multi-scale segmentation technique feature a collection of pixels into homogenous,as the object.Then,based on the spectral,spatial,texture and neighborhood characteristic of objects,we establish landslide recognition rules to extract landslide areas.The results show that the object-oriented technology can better extract loess landslide hazard information.关键词
黑方台滑坡/黄土滑坡/面向对象/多尺度分割/滑坡识别/甘肃永靖Key words
the Heifangtai landslide/loose landslide/object-oriented analysis/multi-scale segmentation, detection of landslide/Yongjing in Gansu分类
资源环境引用本文复制引用
张群,赵超英..基于面向对象的高分遥感数据甘肃黑方台黄土滑坡半自动识别[J].灾害学,2017,32(3):210-215,6.基金项目
国家自然科学基金“危岩体崩塌灾害InSAR高精度监测关键技术研究”(41372375) （41372375）
国家重点基础研究发展规划(973计划)“黄土重大灾害超前判识、临灾预警与风险控制”(2014CB744703) （973计划）
