基于高光谱遥感影像的建筑物表面材质识别方法（英文）

发布时间：2018-04-05 15:23

本文选题：建筑物材料　切入点：高光谱遥感　出处：《Journal of Zhejiang University-Science A(Applied Physics & Engineering)》2017年12期

【摘要】：目的:建筑物的材质信息是灾害评估和城市调查等领域的重要信息。本文旨在利用高光谱遥感影像提取地面建筑物的表面材质信息(包括材质类型和主要组成成份),并对提取方法进行对比,给出应用建议。创新点:对建筑物材料进行光谱测试,并对其高光谱响应规律进行分析,找出有诊断意义的光谱位置;基于实验和验证得出应用方法的适应性,以提高信息提取精度。方法:1.设计建筑物材质信息提取流程(图1),并对高光谱数据进行基础处理;2.对建筑物材料进行光谱测试(波长范围为350~2500 nm,图3),并完成各类建筑物的诊断性光谱分析;3.利用光谱角度法(公式(1))和光谱信息散度法(公式(2))进行材质信息提取(图5和6);4.综合分析两种方法的应用过程与控制参数和准确率的关系。结论:1.两种方法皆可提取建筑物材质信息,但在应用过程中需要进行参数的适应性调整,这是提高准确率的关键;2.在建筑物材质信息提取方面,光谱角度法的提取准确率略高于光谱散度法。
[Abstract]:Objective: material information of buildings is an important information in disaster assessment and urban survey.The purpose of this paper is to use hyperspectral remote sensing image to extract the surface material information of ground buildings (including material types and main components), and to compare the extraction methods and give some suggestions for application.Innovation: spectral testing of building materials and analysis of hyperspectral response law to find diagnostic spectral position; based on experiments and validation to obtain the adaptability of the application methods in order to improve the accuracy of information extraction.Method 1: 1.Design building material information extraction process (fig. 1), and carry out basic processing of hyperspectral data.Spectral measurements of building materials (wavelength range 350 ~ 2 500 nm, fig. 3), and diagnostic spectral analysis of all kinds of buildings have been completed.The spectral angle method (formula 1) and spectral information divergence method (formula 2) were used to extract the material information (fig. 5 and 6 / 4).The relationship between the application process of the two methods and the control parameters and accuracy is analyzed synthetically.Conclusion 1.Both methods can extract the building material information, but in the process of application, we need to adjust the parameters adaptively, which is the key to improve the accuracy.In the information extraction of building materials, the accuracy of spectral angle method is slightly higher than that of spectral divergence method.
【作者单位】： Key
【基金】：supported by the National Key Technologies R&D Program of China(No.2016YFB0502603) the Key Project of Sichuan Provincial Education Department(No.2018LG113),China
【分类号】：P237;TU50

【相似文献】