泥石流高分辨率遥感影像频域特征提取方法及应用  

Frequency domain feature extraction method and application of high⁃resolution remote sensing image of debris flow

作　　者：张悦 张锦[1] ZHANG Yue;ZHANG Jin(College of Engineering,Taiyuan University of Technology,Taiyuan 030006,China)

机构地区：[1]太原理工大学矿业工程学院,山西太原030006

出　　处：《测绘通报》2023年第3期111-115,共5页Bulletin of Surveying and Mapping

基　　金：国家自然科学基金面上项目(42171424);国家重点研发计划(2018YFB0505402)。

摘　　要：在遥感影像上深入研究泥石流的相关特征条件对泥石流的分析治理具有十分重要的现实意义。本文将泥石流不同流域分区的高分辨率遥感影像从空间域转换到频率域,基于频谱分析与频域滤波,从全局和局部建立了频谱特征和泥石流流域分区特征之间的关联,并利用频域特征对泥石流高分辨率遥感影像中不同流域分区进行识别,用支持向量机进行试验验证。结果表明,对于泥石流遥感影像,除了地物光谱特性以外,充分利用频域特征可以有效地分析和识别泥石流不同的流域分区,且识别精度最高达到95%,从而对泥石流的形成过程及不同区域进行定性和定量分析,为泥石流的防治工作提供了科学依据。It is of great practical significance to lucubrate characteristics of debris flow on remote sensing image.The study converts high⁃resolution remote sensing images of different watershed regions of debris flow from spatial domain to frequency domain.Based on the spectrum analysis and frequency domain filtering,the study establishes correlation between the spectral features and partition features of the debris flow globally and locally,and identifies different watershed regions in the high⁃resolution remote sensing image of debris flow,finally texts it with support vector machine.The results show that making full use of frequency domain features can effectively analyze and identify different watershed regions of debris flow in addition to the spectral characteristics,and the identification accuracy is up to 95%.Thus,we can qualitative and quantitative analysis the formation process of debris flow and different areas,providing scientific basis for the prevention and control of debris flow.

关 键 词：高分辨率遥感影像 泥石流 频谱分析 频域滤波 

分 类 号：P237[天文地球—摄影测量与遥感]